Image quality assessment: from error visibility to structural similarity

2004/04/01 by Zhou Wang, A.C. Bovik, H.R. Sheikh +1 · 1,576 citations

paper · doi:10.1109/tip.2003.819861

Cited by

• ROGR: Relightable 3D Objects using Generative Relighting
• CASIAL: Geometric Distortion Robust Image Watermarking
• 3DGBGS: 3D Granular Ball Gaussian Splatting for Compact Novel View Synthesis
• Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control
• SpatialQ: Understanding 3D Gaussian Splatting Scene Quality via Visual-based MLLM
• StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation
• WildShadowRemover: In-the-Wild Video Shadow Removal via Detail-Preserving Video Diffusion Models
• Weight and Height Estimation from a Single Human Image Captured in the Wild
• Mask2IV: Interaction-Centric Video Generation via Mask Trajectories
• Input-Aware Sparse Attention for Real-Time Co-Speech Video Generation
• Robust 4D Driving Scene Reconstruction from Imperfect Visual Priors
• A Relaxed Gradient Step Denoiser for Splitting Methods in Poisson Inverse Problems
• InkShield: Writing Style Protection Against Unauthorized Handwriting Mimicry
• Robust RPC Bundle Adjustment for Multi-Date Satellite Imagery with Season-Invariant Correspondences
• Calibrated Pressure-Observable Born and Hessian Actions for Quantum-Assisted Waveform Inversion
• UniForward: Unified 3D Scene and Semantic Field Reconstruction via Feed-Forward Gaussian Splatting from Only Sparse-View Images
• Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving
• Learning Developmental Scaffoldings to Guide Self-Organisation
• SceneExpander: Text-Guided 3D Scene Expansion via Free-Form View Insertion
• Walk through Paintings: Egocentric World Models from Internet Priors
• HGC-Avatar: Hierarchical Gaussian Compression for Streamable Dynamic 3D Avatars
• Seeing Clearly and Deeply: An RGBD Imaging Approach with a Bio-inspired Monocentric Design
• Recover Biological Structure from Sparse-View Diffraction Images with Neural Volumetric Prior
• Larger Hausdorff Dimension in Scanning Pattern Facilitates Mamba-Based Methods in Low-Light Image Enhancement
• Group Relative Attention Guidance for Image Editing
• A Luminance-Aware Multi-Scale Network for Polarization Image Fusion with a Multi-Scene Dataset
• High-Quality and Large-Scale Image Downscaling for Modern Display Devices
• See the Speaker: Crafting High-Resolution Talking Faces from Speech with Prior Guidance and Region Refinement
• Variable Projected Augmented Lagrangian Methods for Generalized Lasso Problems
• Differential Privacy: Gradient Leakage Attacks in Federated Learning Environments
• A Survey on Collaborative SLAM with 3D Gaussian Splatting
• Neural USD: An object-centric framework for iterative editing and control
• Adaptive Keyframe Selection for Scalable 3D Scene Reconstruction in Dynamic Environments
• Fast and scalable joint-LORAKS reconstruction and data-driven sampling optimisation of high-dimensional MRI datasets using a GPU-accelerated and learning-free differentiable framework: PyLORAKS
• Super-recognizers sample visual information of superior computational value for facial recognition
• Low-Dose CT Imaging Using a Regularization-Enhanced Efficient Diffusion Probabilistic Model
• Semantic-Guided Cross-Sensor Super Resolution of Remote Sensing Images: A Gated Dual Conditioning Flow Matching Model
• A global inverse-problem approach to quantitative photo-switching optoacoustic mesoscopy
• MMTutorBench: The First Multimodal Benchmark for AI Math Tutoring
• Equivariance2Inverse: A Practical Self-Supervised CT Reconstruction Method Benchmarked on Real, Limited-Angle, and Blurred Data
• ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation
• Residual Diffusion Bridge Model for Image Restoration
• Seeing Through the Brain: New Insights from Decoding Visual Stimuli with fMRI
• ESCA: Enabling Seamless Codec Avatar Execution through Algorithm and Hardware Co-Optimization for Virtual Reality
• MAGIC-Talk: Motion-aware Audio-Driven Talking Face Generation with Customizable Identity Control
• RoboSVG: A Unified Framework for Interactive SVG Generation with Multi-modal Guidance
• Learning Event-guided Exposure-agnostic Video Frame Interpolation via Adaptive Feature Blending
• Structure Aware Image Downscaling
• Low-Light Image Enhancement Using Gamma Learning And Attention-Enabled Encoder-Decoder Networks
• SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning
• DynaPose4D: High-Quality 4D Dynamic Content Generation via Pose Alignment Loss
• TraceTrans: Translation and Spatial Tracing for Surgical Prediction
• GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation
• Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction
• I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions
• Frequency-Spatial Interaction Driven Network for Low-Light Image Enhancement
• Scanner-Agnostic MRI Harmonization via SSIM-Guided Disentanglement
• MAGIC-Flow: Multiscale Adaptive Conditional Flows for Generation and Interpretable Classification
• FlowOpt: Fast Optimization Through Whole Flow Processes for Training-Free Editing
• Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
• LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal
• Depth-Supervised Fusion Network for Seamless-Free Image Stitching
• Cold-Diffusion Driven Downward Continuation of Gravity Data
• Video Prediction of Dynamic Physical Simulations With Pixel-Space Spatiotemporal Transformers
• MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs
• Active control the peak value of Hanbury Brown-Twiss effect with classical light by holographic projection
• Positional Encoding Field
• Lightweight CycleGAN Models for Cross-Modality Image Transformation and Experimental Quality Assessment in Fluorescence Microscopy
• EditInfinity: Image Editing with Binary-Quantized Generative Models
• Target-aware Image Editing via Cycle-consistent Constraints
• Inverse Image-Based Rendering for Light Field Generation from Single Images
• From Far and Near: Perceptual Evaluation of Crowd Representations Across Levels of Detail
• Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging
• Curvilinear Structure-preserving Unpaired Cross-domain Medical Image Translation
• VGD: Visual Geometry Gaussian Splatting for Feed-Forward Surround-view Driving Reconstruction
• BrainCognizer: Brain Decoding with Human Visual Cognition Simulation for fMRI-to-Image Reconstruction
• BrainMCLIP: Brain Image Decoding with Multi-Layer feature Fusion of CLIP
• BrainPuzzle: Hybrid Physics and Data-Driven Reconstruction for Transcranial Ultrasound Tomography
• GRASPLAT: Enabling dexterous grasping through novel view synthesis
• HDR Image Reconstruction using an Unsupervised Fusion Model
• Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos
• FeatureFool: Zero-Query Fooling of Video Models via Feature Map
• Decoding Dynamic Visual Experience from Calcium Imaging via Cell-Pattern-Aware Pretraining
• DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
• Adapting Stereo Vision From Objects To 3D Lunar Surface Reconstruction with the StereoLunar Dataset
• ConsistEdit: Highly Consistent and Precise Training-free Visual Editing
• RaindropGS: A Benchmark for 3D Gaussian Splatting under Raindrop Conditions
• Initialize to Generalize: A Stronger Initialization Pipeline for Sparse-View 3DGS
• Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories
• Semantic-E2VID: a Semantic-Enriched Paradigm for Event-to-Video Reconstruction
• iDETEX: Empowering MLLMs for Intelligent DETailed EXplainable IQA
• CharDiff-LP: A Diffusion Model with Character-Level Guidance for License Plate Image Restoration
• Rethinking Nighttime Image Deraining via Learnable Color Space Transformation
• Prominence-Aware Artifact Detection and Dataset for Image Super-Resolution
• 2DGS-R: Revisiting the Normal Consistency Regularization in 2D Gaussian Splatting
• A Comprehensive Survey on World Models for Embodied AI
• A GAN-Based Framework for Generating STFT Spectrograms of Rare Acoustic Events in Structural Health Monitoring
• Personalized Image Filter: Mastering Your Photographic Style
• Latent Diffusion Model without Variational Autoencoder
• Compressive Modeling and Visualization of Multivariate Scientific Data using Implicit Neural Representation
• Cost Savings from Automatic Quality Assessment of Generated Images
• GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer
• Deep generative priors for 3D brain analysis
• Galaxy Morphology Classification with Counterfactual Explanation
• SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images
• LightQANet: Quantized and Adaptive Feature Learning for Low-Light Image Enhancement
• Inpainting the Red Planet: Diffusion Models for the Reconstruction of Martian Environments in Virtual Reality
• LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching
• BalanceGS: Algorithm-System Co-design for Efficient 3D Gaussian Splatting Training on GPU
• Exploring Image Representation with Decoupled Classical Visual Descriptors
• Acquisition of interpretable domain information during brain MR image harmonization for content-based image retrieval
• MACE: Mixture-of-Experts Accelerated Coordinate Encoding for Large-Scale Scene Localization and Rendering
• cubic: CUDA-accelerated 3D Bioimage Computing
• ViTacGen: Robotic Pushing with Vision-to-Touch Generation
• NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results
• An efficient approach with theoretical guarantees to simultaneously reconstruct activity and attenuation sinogram for TOF-PET
• MRSeqStudio: MRI Sequence Design and Simulation as a Service in a Free and Open-Source Web Platform
• SWIR-LightFusion: Multi-spectral Semantic Fusion of Synthetic SWIR with Thermal IR (LWIR/MWIR) and RGB
• Edit-Your-Interest: Efficient Video Editing via Feature Most-Similar Propagation
• No-Reference Rendered Video Quality Assessment: Dataset and Metrics
• Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models
• SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms
• Wavefront Coding for Accommodation-Invariant Near-Eye Displays
• FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
• MS-GAGA: Metric-Selective Guided Adversarial Generation Attack
• DrivingScene: A Multi-Task Online Feed-Forward 3D Gaussian Splatting Method for Dynamic Driving Scenes
• Readout Representation: Redefining Neural Codes by Input Recovery
• UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering
• MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics
• Test-Time Anchoring for Discrete Diffusion Posterior Sampling
• MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference
• Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment
• InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models
• Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency
• NeuroSwift: A Lightweight Cross-Subject Framework for fMRI Visual Reconstruction of Complex Scenes
• Bit Allocation Transfer for Perceptual Quality Enhancement of VVC Intra Coding
• Blade: A Derivative-free Bayesian Inversion Method using Diffusion Priors
• Towards Distribution-Shift Uncertainty Estimation for Inverse Problems with Generative Priors
• Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements
• Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos
• JND-Guided Light-Weight Neural Pre-Filter for Perceptual Image Coding
• Towards Efficient 3D Gaussian Human Avatar Compression: A Prior-Guided Framework
• VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework
• Sketch Animation: State-of-the-art Report
• Gesplat: Robust Pose-Free 3D Reconstruction via Geometry-Guided Gaussian Splatting
• Enabling High-Quality In-the-Wild Imaging from Severely Aberrated Metalens Bursts
• Local-Global Context-Aware and Structure-Preserving Image Super-Resolution
• CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting
• BurstDeflicker: A Benchmark Dataset for Flicker Removal in Dynamic Scenes
• FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering
• Generative Latent Video Compression
• Ctrl-World: A Controllable Generative World Model for Robot Manipulation
• A Style-Based Profiling Framework for Quantifying the Synthetic-to-Real Gap in Autonomous Driving Datasets
• Simulation-based inference at the theoretical limit for fast, robust microstructural MRI with minimal diffusion data
• MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs
• Harnessing Self-Supervised Deep Learning and Geostationary Remote Sensing for Advancing Wildfire and Associated Air Quality Monitoring: Improved Smoke and Fire Front Masking using GOES and TEMPO Radiance Data
• Few-shot multi-token DreamBooth with LoRa for style-consistent character generation
• Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation
• SynthID-Image: Image watermarking at internet scale
• RoDyn: Taming Interactive Robot-Dynamic 2.5D World Model for Robotic Manipulation
• FS-RWKV: Leveraging Frequency Spatial-Aware RWKV for 3T-to-7T MRI Translation
• PC-UNet: An Enforcing Poisson Statistics U-Net for Positron Emission Tomography Denoising
• Defense against Unauthorized Distillation in Image Restoration via Feature Space Perturbation
• Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark
• HandEval: Taking the First Step Towards Hand Quality Evaluation in Generated Images
• UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction
• Median2Median: Zero-shot Suppression of Structured Noise in Images
• HeadsUp! High-Fidelity Portrait Image Super-Resolution
• Q-Router: Agentic Video Quality Assessment with Expert Model Routing and Artifact Localization
• LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution
• SAFER-AiD: Saccade-Assisted Foveal-peripheral vision Enhanced Reconstruction for Adversarial Defense
• X2Video: Adapting Diffusion Models for Multimodal Controllable Neural Video Rendering
• FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching
• Spectral Prefiltering of Neural Fields
• Variable-Rate Texture Compression: Real-Time Rendering with JPEG
• SatFusion: A Unified Framework for Enhancing Remote Sensing Images via Multi-Frame and Multi-Source Images Fusion
• FlowLensing: Simulating Gravitational Lensing with Flow Matching
• Interlaced dynamic XCT reconstruction with spatio-temporal implicit neural representations
• SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction
• PIT-QMM: A Large Multimodal Model For No-Reference Point Cloud Quality Assessment
• Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight
• Biology-driven assessment of deep learning super-resolution imaging of the porosity network in dentin
• Once Is Enough: Lightweight DiT-Based Video Virtual Try-On via One-Time Garment Appearance Injection
• ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation
• Splat the Net: Radiance Fields with Splattable Neural Primitives
• Low-Compute Watermark Removal via Dual-Domain Natural Projection
• Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Sampling
• WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation
• MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis
• MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency
• MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics
• Accelerating wave simulations with neural dispersion correctors
• SCas4D: Structural Cascaded Optimization for Boosting Persistent 4D Novel View Synthesis
• RTGS: Real-Time 3D Gaussian Splatting SLAM via Multi-Level Redundancy Reduction
• SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation
• How Confident are Video Models? Empowering Video Models to Express their Uncertainty
• Benchmarking Fake Voice Detection in the Fake Voice Generation Arms Race
• TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation
• Active Next-Best-View Optimization for Risk-Averse Path Planning
• We Can Hide More Bits: The Unused Watermarking Capacity in Theory and in Practice
• Mapping surface height dynamics to subsurface flow physics in free-surface turbulent flow using a shallow recurrent decoder
• Diffusion Models for Low-Light Image Enhancement: A Multi-Perspective Taxonomy and Performance Analysis
• Life at the extremes: maximally divergent microbes with similar genomic signatures linked to extreme environments
• Learning the detector in optical tomography
• Learning a distance measure from the information-estimation geometry of data
• SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization
• CLEAR-IR: Clarity-Enhanced Active Reconstruction of Infrared Imagery
• MACS: Measurement-Aware Consistency Sampling for Inverse Problems
• VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery
• No-reference Quality Assessment of Contrast-distorted Images using Contrast-enhanced Pseudo Reference
• QuantDemoire: Quantization with Outlier Aware for Image Demoiréing
• Adaptive double-phase Rudin--Osher--Fatemi denoising model
• The 1st Solution for CARE Liver Task Challenge 2025: Contrast-Aware Semi-Supervised Segmentation with Domain Generalization and Test-Time Adaptation
• Super-resolution image projection over an extended depth of field using a diffractive decoder
• DHQA-4D: Perceptual Quality Assessment of Dynamic 4D Digital Human
• Contrastive-SDE: Guiding Stochastic Differential Equations with Contrastive Learning for Unpaired Image-to-Image Translation
• LoRA Patching: Exposing the Fragility of Proactive Defenses against Deepfakes
• Exploring Instruction Data Quality for Explainable Image Quality Assessment
• AortaDiff: A Unified Multitask Diffusion Framework For Contrast-Free AAA Imaging
• HAVIR: HierArchical Vision to Image Reconstruction using CLIP-Guided Versatile Diffusion
• Latent Diffusion Unlearning: Protecting Against Unauthorized Personalization Through Trajectory Shifted Perturbations
• PocketSR: The Super-Resolution Expert in Your Pocket Mobiles
• Towards Scalable and Consistent 3D Editing
• Flip Distribution Alignment VAE for Multi-Phase MRI Synthesis
• GS-Share: Enabling High-fidelity Map Sharing with Incremental Gaussian Splatting
• Net2Net: When Un-trained Meets Pre-trained Networks for Robust Real-World Denoising
• From Tokens to Nodes: Semantic-Guided Motion Control for Dynamic 3D Gaussian Splatting
• Image Enhancement Based on Pigment Representation
• FSFSplatter: Build Surface and Novel Views with Sparse-Views within 2min
• Longitudinal Flow Matching for Trajectory Modeling
• LVTINO: LAtent Video consisTency INverse sOlver for High Definition Video Restoration
• EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
• Visual Self-Refinement for Autoregressive Models
• Equivariant Splitting: Self-supervised learning from incomplete data
• DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models
• SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition
• Geometric Spatio-Spectral Total Variation for Hyperspectral Image Denoising and Destriping
• ZQBA: Zero Query Black-box Adversarial Attack
• InfVSR: Toward Consistency-Driven Streaming Generative Video Super-Resolution
• PhraseStereo: The First Open-Vocabulary Stereo Image Segmentation Dataset
• Universal Beta Splatting
• Observer-Usable Information as a Task-specific Image Quality Metric
• MOLM: Mixture of LoRA Markers
• Secure and Robust Watermarking for AI-generated Images: A Comprehensive Survey
• HART: Human Aligned Reconstruction Transformer
• PRISM: Progressive Rain removal with Integrated State-space Modeling
• AgenticIQA: An Agentic Framework for Adaptive and Interpretable Image Quality Assessment
• Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
• Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation
• GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification
• Flow Matching with Semidiscrete Couplings
• FlashOmni: A Unified Sparse Attention Engine for Diffusion Transformers
• DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
• MANI-Pure: Magnitude-Adaptive Noise Injection for Adversarial Purification
• Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner
• ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation
• Environment-Aware Satellite Image Generation with Diffusion Models
• NeuralPVS: Learned Estimation of Potentially Visible Sets
• RIFLE: Removal of Image Flicker-Banding via Latent Diffusion Enhancement
• SAIP: A Plug-and-Play Scale-adaptive Module in Diffusion-based Inverse Problems
• OMeGa: Joint Optimization of Explicit Meshes and Gaussian Splats for Robust Scene-Level Surface Reconstruction
• Asymmetric VAE for One-Step Video Super-Resolution Acceleration
• World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
• Synergizing scientific and local knowledge for ecosystem services assessments: A case study in northern Portugal
• GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
• Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis
• Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution
• Tunable-Generalization Diffusion Powered by Self-Supervised Contextual Sub-Data for Low-Dose CT Reconstruction
• Texture Vector-Quantization and Reconstruction Aware Prediction for Generative Super-Resolution
• HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation
• Latent Representation Learning from 3D Brain MRI for Interpretable Prediction in Multiple Sclerosis
• BioVessel-Net and RetinaMix: Unsupervised Retinal Vessel Segmentation from OCTA Images
• FlowLUT: Efficient Image Enhancement via Differentiable LUTs and Iterative Flow Matching
• Foundation Model-Based Adaptive Semantic Image Transmission for Dynamic Wireless Environments
• Towards Interpretable Visual Decoding with Attention to Brain Representations
• FM-SIREN & FM-FINER: Nyquist-Informed Frequency Multiplier for Implicit Neural Representation with Periodic Activation
• OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting
• Enhanced Quality Aware-Scalable Underwater Image Compression
• ARSS: Taming Decoder-only Autoregressive Visual Generation for View Synthesis From Single View
• Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing
• Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos
• Enhancing Blind Face Restoration through Online Reinforcement Learning
• WoW: Towards a World omniscient World model Through Embodied Interaction
• CCNeXt: An Effective Self-Supervised Stereo Depth Estimation Approach
• SSVIF: Self-Supervised Segmentation-Oriented Visible and Infrared Image Fusion
• LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion Transformer
• FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing
• Clinical Uncertainty Impacts Machine Learning Evaluations
• DragGANSpace: Latent Space Exploration and Control for GANs
• REFINE-CONTROL: A Semi-supervised Distillation Method For Conditional Image Generation
• No-Reference Image Contrast Assessment with Customized EfficientNet-B0
• TDEdit: A Unified Diffusion Framework for Text-Drag Guided Image Manipulation
• SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit 3D Meshes
• RED-DiffEq: Regularization by denoising diffusion models for solving inverse PDE problems with application to full waveform inversion
• Filtering with Confidence: When Data Augmentation Meets Conformal Prediction
• Does FLUX Already Know How to Perform Physically Plausible Image Composition?
• A Hierarchical Variational Graph Fused Lasso for Recovering Relative Rates in Spatial Compositional Data
• The Unanticipated Asymmetry Between Perceptual Optimization and Assessment
• ControlHair: Synergizing Physics Simulator and Video Diffusion for Controllable Dynamic Hair Rendering
• MotionFlow:Learning Implicit Motion Flow for Complex Camera Trajectory Control in Video Generation
• Efficient Encoder-Free Pose Conditioning and Pose Control for Virtual Try-On
• An Anisotropic Cross-View Texture Transfer with Multi-Reference Non-Local Attention for CT Slice Interpolation
• JaiLIP: Jailbreaking Vision-Language Models via Loss Guided Image Perturbation
• Downscaling climate projections to 1 km with single-image super resolution
• Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing
• CamPVG: Camera-Controlled Panoramic Video Generation with Epipolar-Aware Diffusion
• SynchroRaMa : Lip-Synchronized and Emotion-Aware Talking Face Generation via Multi-Modal Emotion Embedding
• AJAHR: Amputated Joint Aware 3D Human Mesh Recovery
• Talking Head Generation via AU-Guided Landmark Prediction
• Raw-JPEG Adapter: Efficient Raw Image Compression with JPEG
• Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components
• CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensing image restoration
• FeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion Inference
• S-Avatar: Diffusion-Guided Gaussian Head Avatars from a Single Image
• RFMSR: Residual Flow Matching for Image Super-Resolution
• FDDWAN: A Frequency-Decoupled Diffusion Network for Watermarking Attack
• Collaborative feature aggregation for face super-resolution and robust re-identification
• Split and Drive: Dual-Axis Disentanglement for Real-Time Gaussian Head Avatars
• Convolutional neural shading for high-quality 3D reconstruction from multi-view images
• What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration
• Now You Have My Healthy Attention: A U-DiT for Brain-MRI Inpainting
• Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer
• IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks
• Metric-Guided Synthetic Image Data Rendering for Deep Learning compatible with Agentic AI
• Generative Relightable Avatars
• SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation
• Habitability Study of Terrestrial Planets: Application to Venus-like Worlds
• StrIPETrack : a real-time, ROI-flexible tracking platform for high-throughput zebrafish behavior
• Dark3R: Learning Structure from Motion in the Dark
• Warm Chat: Diffuse Emotion-aware Interactive Talking Head Avatar with Tree-Structured Guidance
• Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation
• SeHDR: Single-Exposure HDR Novel View Synthesis via 3D Gaussian Bracketing
• Adversarially-Refined VQ-GAN with Dense Motion Tokenization for Spatio-Temporal Heatmaps
• RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions
• Audio-Driven Universal Gaussian Head Avatars
• DeblurSplat: SfM-free 3D Gaussian Splatting with Event Camera for Robust Deblurring
• FlowCrypt: Flow-Based Lightweight Encryption with Near-Lossless Recovery for Cloud Photo Privacy
• NGD: Neural Gradient Based Deformation for Monocular Garment Reconstruction
• CATformer: Contrastive Adversarial Transformer for Image Super-Resolution
• GeoRemover: Removing Objects and Their Causal Visual Artifacts
• FixingGS: Enhancing 3D Gaussian Splatting via Training-Free Score Distillation
• SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack against No-Reference Image Quality Assessment Models
• VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
• Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic Guidance
• 4D-MoDe: Towards Editable and Scalable Volumetric Streaming via Motion-Decoupled 4D Gaussian Compression
• Audio Super-Resolution with Latent Bridge Models
• Learning Neural Antiderivatives
• RadarSFD: Single-Frame Diffusion with Pretrained Priors for Radar Point Clouds
• LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation
• StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models
• Clothing agnostic Pre-inpainting Virtual Try-ON
• SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
• Modeling Bottom-up Information Quality during Language Processing
• Attentive AV-FusionNet: Audio-Visual Quality Prediction with Hybrid Attention
• SemanticGarment: Semantic-Controlled Generation and Editing of 3D Gaussian Garments
• PhysHDR: When Lighting Meets Materials and Scene Geometry in HDR Reconstruction
• HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis
• Task-Oriented Communications for 3D Scene Representation: Balancing Timeliness and Fidelity
• MobileUPReg: Identifying User-Perceived Performance Regressions in Mobile OS Versions
• A Multi-Grid Implicit Neural Representation for Multi-View Videos
• A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis
• JCo-MVTON: Jointly Controllable Multi-Modal Diffusion Transformer for Mask-Free Virtual Try-on
• GWM: Towards Scalable Gaussian World Models for Robotic Manipulation
• Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation
• LenslessMic: Audio Encryption and Authentication via Lensless Computational Imaging
• Neural Atlas Graphs for Dynamic Scene Decomposition and Editing
• Uniform 2D Target Generation via Inverse-designed Metasurfaces
• Spatio-temporal, multi-field deep learning of shock propagation in meso-structured media
• SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling
• ChartMaster: Advancing Chart-to-Code Generation with Real-World Charts and Chart Similarity Reinforcement Learning
• Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach
• SAMPO:Scale-wise Autoregression with Motion PrOmpt for generative world models
• Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects
• MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild
• Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution
• SPATIALGEN: Layout-guided 3D Indoor Scene Generation
• Controllable Localized Face Anonymization Via Diffusion Inpainting
• Dataset Distillation for Super-Resolution without Class Labels and Pre-trained Models
• The Describe-Then-Generate Bottleneck: How VLM Descriptions Alter Image Generation Outcomes
• OpenViGA: Video Generation for Automotive Driving Scenes by Streamlining and Fine-Tuning Open Source Models with Public Data
• TinySR: Pruning Diffusion for Real-World Image Super-Resolution
• BemaGANv2: Discriminator Combination Strategies for GAN-based Vocoders in Long-Term Audio Generation
• ProFusion: 3D Reconstruction of Protein Complex Structures from Multi-view AFM Images
• LamiGauss: Pitching Radiative Gaussian for Sparse-View X-ray Laminography Reconstruction
• Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
• Condition Weaving Meets Expert Modulation: Towards Universal and Controllable Image Generation
• A Hybrid Approach for Unified Image Quality Assessment: Permutation Entropy-Based Features Fused with Random Forest for Natural-Scene and Screen-Content Images for Cross-Content Applications
• Assessing Data Replication in Symbolic Music via Adapted Structural Similarity Index Measure
• Stochastic ion emission perturbation mechanisms in atom probe tomography: Linking simulations to experiment
• UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry
• FoundDiff: Foundational Diffusion Model for Generalizable Low-Dose CT Denoising
• DEFT-VTON: Efficient Virtual Try-On with Consistent Generalised H-Transform
• Improving 3D Gaussian Splatting Compression by Scene-Adaptive Lattice Vector Quantization
• Temporally Smooth Mesh Extraction for Procedural Scenes with Long-Range Camera Trajectories using Spacetime Octrees
• Deep learning approach for flow visualization in background-oriented schlieren
• Improving Muon Scattering Tomography Performance With A Muon Momentum Measurement Scheme
• Deep Learning Architectures for Medical Image Denoising: A Comparative Study of CNN-DAE, CADTra, and DCMIEDNet
• Evaluation of Objective Image Quality Metrics for High-Fidelity Image Compression
• A Statistical Benchmark for Diffusion Posterior Sampling Algorithms
• Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics
• Unrolling Graph-based Douglas-Rachford Algorithm for Image Interpolation with Informed Initialization
• Impact of a Sharpness Based Loss Function for Removing Out-of-Focus Blur
• LaGarNet: Goal-Conditioned Recurrent State-Space Models for Pick-and-Place Garment Flattening
• Modality-Aware Infrared and Visible Image Fusion with Target-Aware Supervision
• ROSGS: Relightable Outdoor Scenes With Gaussian Splatting
• SVR-GS: Spatially Variant Regularization for Probabilistic Masks in 3D Gaussian Splatting
• Synthetic Dataset Evaluation Based on Generalized Cross Validation
• Dual Orthogonal Guidance for Robust Diffusion-based Handwritten Text Generation
• Every Camera Effect, Every Time, All at Once: 4D Gaussian Ray Tracing for Physics-based Camera Effect Data Generation
• Mask Consistency Regularization in Object Removal
• A Lightweight Ensemble-Based Face Image Quality Assessment Method with Correlation-Aware Loss
• Adaptive Token Merging for Efficient Transformer Semantic Communication at the Edge
• RPD-Diff: Region-Adaptive Physics-Guided Diffusion Model for Visibility Enhancement under Dense and Non-Uniform Haze
• FS-Diff: Semantic guidance and clarity-aware simultaneous multimodal image fusion and super-resolution
• Data-Driven Discovery of Emergent Dynamics in Reaction-Diffusion Systems from Sparse and Noisy Observations
• VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Results
• Objectness Similarity: Capturing Object-Level Fidelity in 3D Scene Evaluation
• MDIQA: Unified Image Quality Assessment for Multi-dimensional Evaluation and Restoration
• Investigating the Impact of Various Loss Functions and Learnable Wiener Filter for Laparoscopic Image Desmoking
• Images in Motion?: A First Look into Video Leakage in Collaborative Deep Learning
• An U-Net-Based Deep Neural Network for Cloud Shadow and Sun-Glint Correction of Unmanned Aerial System (UAS) Imagery
• GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts
• Using machine learning to downscale coarse-resolution environmental variables for understanding the spatial frequency of convective storms
• AdsQA: Towards Advertisement Video Understanding
• Prompt-Driven Image Analysis with Multimodal Generative AI: Detection, Segmentation, Inpainting, and Interpretation
• First-order State Space Model for Lightweight Image Super-resolution
• Sparse Transformer for Ultra-sparse Sampled Video Compressive Sensing
• LD-ViCE: Latent Diffusion Model for Video Counterfactual Explanations
• Spectral Bottleneck in Sinusoidal Representation Networks: Noise is All You Need
• SplatFill: 3D Scene Inpainting via Depth-Guided Gaussian Splatting
• DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation
• XOCT: Enhancing OCT to OCTA Translation via Cross-Dimensional Supervised Multi-Scale Feature Learning
• Faster, Self-Supervised Super-Resolution for Anisotropic Multi-View MRI Using a Sparse Coordinate Loss
• GAICo: A Deployed and Extensible Framework for Evaluating Diverse and Multimodal Generative AI Outputs
• Privacy Preserving Semantic Communications Using Vision Language Models: A Segmentation and Generation Approach
• Evaluation of Machine Learning Reconstruction Techniques for Accelerated Brain MRI Scans
• Diffusion-Shock PDEs for Deep Learning on Position-Orientation Space
• Perception-oriented Bidirectional Attention Network for Image Super-resolution Quality Assessment
• AIM 2025 Challenge on High FPS Motion Deblurring: Methods and Results
• Learning in ImaginationLand: Omnidirectional Policies through 3D Generative Models (OP-Gen)
• Time-Aware One Step Diffusion Network for Real-World Image Super-Resolution
• SpecSwin3D: Generating Hyperspectral Imagery from Multispectral Data via Transformer Networks
• Dual-Mode Deep Anomaly Detection for Medical Manufacturing: Structural Similarity and Feature Distance
• Hybrid-illumination multiplexed Fourier ptychographic microscopy with robust aberration correction
• Systematic Review and Meta-analysis of AI-driven MRI Motion Artifact Detection and Correction
• Reverse Browser: Vector-Image-to-Code Generator
• CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus
• Human Motion Video Generation: A Survey
• A Neural Network Approach to Multi-radionuclide TDCR Beta Spectroscopy
• PromptFlare: Prompt-Generalized Defense via Cross-Attention Decoy in Diffusion-Based Inpainting
• OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models
• Deep learning-enabled virtual multiplexed immunostaining of label-free tissue for vascular invasion assessment
• Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing
• RAGSR: Regional Attention Guided Diffusion for Image Super-Resolution
• STZ: A High Quality and High Speed Streaming Lossy Compression Framework for Scientific Data
• Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling
• Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables
• MILO: A Lightweight Perceptual Quality Metric for Image and Latent-Space Optimization
• Unsupervised Ultra-High-Resolution UAV Low-Light Image Enhancement: A Benchmark, Metric and Framework
• PRINTER:Deformation-Aware Adversarial Learning for Virtual IHC Staining with In Situ Fidelity
• DynaMind: Reconstructing Dynamic Visual Scenes from EEG by Aligning Temporal Dynamics and Multimodal Semantics to Guided Diffusion
• A Unified Low-level Foundation Model for Enhancing Pathology Image Quality
• Seeing through Unclear Glass: Occlusion Removal with One Shot
• Delta Rectified Flow Sampling for Text-to-Image Editing
• GaussianGAN: Real-Time Photorealistic controllable Human Avatars
• Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion
• UPGS: Unified Pose-aware Gaussian Splatting for Dynamic Scene Deblurring
• DevilSight: Augmenting Monocular Human Avatar Reconstruction through a Virtual Perspective
• DAOVI: Distortion-Aware Omnidirectional Video Inpainting
• LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables
• Low-Rank Regularized Convex-Non-Convex Problems for Image Segmentation or Completion
• Complete Gaussian Splats from a Single Image with Denoising Diffusion Models
• ManipDreamer3D : Synthesizing Plausible Robotic Manipulation Video with Occupancy-aware 3D Trajectory
• Diverse Signer Avatars with Manual and Non-Manual Feature Modelling for Sign Language Production
• Generative AI for Industrial Contour Detection: A Language-Guided Vision System
• Unfolding Framework with Complex-Valued Deformable Attention for High-Quality Computer-Generated Hologram Generation
• First-Place Solution to NeurIPS 2024 Invisible Watermark Removal Challenge
• FusionCounting: Robust visible-infrared image fusion guided by crowd counting via multi-task learning
• Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization
• CoCoL: A Communication Efficient Decentralized Collaborative Method for Multi-Robot Systems
• Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding
• C³-GS: Learning Context-aware, Cross-dimension, Cross-scale Feature for Generalizable Gaussian Splatting
• Disruptive Attacks on Face Swapping via Low-Frequency Perceptual Perturbations
• Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent
• RadGS-Reg: Registering Spine CT with Biplanar X-rays via Joint 3D Radiative Gaussians Reconstruction and 3D/3D Registration
• FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models
• Beyond Imaging: Vision Transformer Digital Twin Surrogates for 3D+T Biological Tissue Dynamics
• Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Models
• StableIntrinsic: Detail-preserving One-step Diffusion Model for Multi-view Material Estimation
• IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoising
• High-Speed FHD Full-Color Video Computer-Generated Holography
• High-Frequency First: A Two-Stage Approach for Improving Image INR
• Task-Generalized Adaptive Cross-Domain Learning for Multimodal Image Fusion
• Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion
• VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
• Mini-Batch Robustness Verification of Deep Neural Networks
• RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration
• Understanding Benefits and Pitfalls of Current Methods for the Segmentation of Undersampled MRI Data
• Alljoined-1.6M: A Million-Trial EEG-Image Dataset for Evaluating Affordable Brain-Computer Interfaces
• Spatial Policy: Guiding Visuomotor Robotic Manipulation with Spatial-Aware Modeling and Reasoning
• ROSE: Remove Objects with Side Effects in Videos
• Wan-S2V: Audio-Driven Cinematic Video Generation
• Evaluating the visual design of science publications—a quantitative approach comparing legitimate and predatory journal papers
• FastAvatar: Instant 3D Gaussian Splatting for Faces from Single Unconstrained Poses
• FCR: Investigating Generative AI models for Forensic Craniofacial Reconstruction
• Zero-shot CT Super-Resolution using Diffusion-based 2D Projection Priors and Signed 3D Gaussians
• Image-Conditioned 3D Gaussian Splat Quantization
• SPIRiT Regularization: Parallel MRI with a Combination of Sensitivity Encoding and Linear Predictability
• HiRQA: Hierarchical Ranking and Quality Alignment for Opinion-Unaware Image Quality Assessment
• Systematic Evaluation of Wavelet-Based Denoising for MRI Brain Images: Optimal Configurations and Performance Benchmarks
• Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds
• CUTE-MRI: Conformalized Uncertainty-based framework for Time-adaptivE MRI
• Entanglement-enhanced imaging through scattering media
• Fine-grained Image Quality Assessment for Perceptual Image Restoration
• NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video Understanding
• Taming Transformer for Emotion-Controllable Talking Face Generation
• Mitigating Data Exfiltration Attacks through Layer-Wise Learning Rate Decay Fine-Tuning
• Improving Resource-Efficient Speech Enhancement via Neural Differentiable DSP Vocoder Refinement
• Reconstruction Using the Invisible: Intuition from NIR and Metadata for Enhanced 3D Gaussian Splatting
• GOGS: High-Fidelity Geometry and Relighting for Glossy Objects via Gaussian Surfels
• LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos
• Distilled-3DGS:Distilled 3D Gaussian Splatting
• Online 3D Gaussian Splatting Modeling with Novel View Selection
• Self-Supervised Sparse Sensor Fusion for Long Range Perception
• DIME-Net: A Dual-Illumination Adaptive Enhancement Network Based on Retinex and Mixture-of-Experts
• Forecasting Smog Events Using ConvLSTM: A Spatio-Temporal Approach for Aerosol Index Prediction in South Asia
• Comparing Conditional Diffusion Models for Synthesizing Contrast-Enhanced Breast MRI from Pre-Contrast Images
• PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis
• Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector
• OmniTry: Virtual Try-On Anything without Masks
• MF-LPR²: Multi-Frame License Plate Image Restoration and Recognition using Optical Flow
• FLAIR: Frequency- and Locality-Aware Implicit Neural Representations
• A Convergent Primal-Dual Algorithm for Computing Rate-Distortion-Perception Functions
• EDTalk++: Full Disentanglement for Controllable Talking Head Synthesis
• Discrete Optimization of Min-Max Violation and its Applications Across Computational Sciences
• Precise Action-to-Video Generation Through Visual Action Prompts
• From Transthoracic to Transesophageal: Cross-Modality Generation using LoRA Diffusion
• Odo: Depth-Guided Diffusion for Identity-Preserving Body Reshaping
• Frequency-Driven Inverse Kernel Prediction for Single Image Defocus Deblurring
• Neural Rendering for Sensor Adaptation in 3D Object Detection
• DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples
• Adaptive Hybrid Caching for Efficient Text-to-Video Diffusion Model Acceleration
• Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models
• DMS:Diffusion-Based Multi-Baseline Stereo Generation for Improving Self-Supervised Depth Estimation
• Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting
• IntelliCap: Intelligent Guidance for Consistent View Sampling
• ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images
• Geometry-Aware Video Inpainting for Joint Headset Occlusion Removal and Face Reconstruction in Social XR
• RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts
• Demystifying Foreground-Background Memorization in Diffusion Models
• DualFit: A Two-Stage Virtual Try-On via Warping and Synthesis
• Guiding WaveMamba with Frequency Maps for Image Debanding
• Unifying Scale-Aware Depth Prediction and Perceptual Priors for Monocular Endoscope Pose Estimation and Tissue Reconstruction
• Tactile Robotics: An Outlook
• Meta-learning Structure-Preserving Dynamics
• Temporally-Similar Structure-Aware Spatiotemporal Fusion of Satellite Images
• Privacy-Aware Detection of Fake Identity Documents: Methodology, Benchmark, and Improved Algorithms (FakeIDet2)
• Self-Supervised Stereo Matching with Multi-Baseline Contrastive Learning
• Object Fidelity Diffusion for Remote Sensing Image Generation
• Ultra-High-Definition Reference-Based Landmark Image Super-Resolution with Generative Diffusion Prior
• Novel View Synthesis using DDIM Inversion
• Physics-Informed Joint Multi-TE Super-Resolution with Implicit Neural Representation for Robust Fetal T2 Mapping
• HM-Talker: Hybrid Motion Modeling for High-Fidelity Talking Head Synthesis
• Physics-Informed Deep Contrast Source Inversion: A Unified Framework for Inverse Scattering Problems
• Multi-Sample Anti-Aliasing and Constrained Optimization for 3D Gaussian Splatting
• TweezeEdit: Consistent and Efficient Image Editing with Path Regularization
• Efficient Image Denoising Using Global and Local Circulant Representation
• SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning
• A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation
• Hybrid Quantum-Classical Latent Diffusion Models for Medical Image Generation
• OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better
• Hierarchical Graph Attention Network for No-Reference Omnidirectional Image Quality Assessment
• In-place Double Stimulus Methodology for Subjective Assessment of High Quality Images
• MangaDiT: Reference-Guided Line Art Colorization with Hierarchical Attention in Diffusion Transformers
• MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography
• DualPhys-GS: Dual Physically-Guided 3D Gaussian Splatting for Underwater Scene Reconstruction
• Images Speak Louder Than Scores: Failure Mode Escape for Enhancing Generative Quality
• GoViG: Goal-Conditioned Visual Navigation Instruction Generation
• SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite Images
• IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding
• Animate-X++: Universal Character Image Animation with Dynamic Backgrounds
• HyperKD: Distilling Cross-Spectral Knowledge in Masked Autoencoders via Inverse Domain Shift with Spatial-Aware Masking and Specialized Loss
• HumanGenesis: Agent-Based Geometric and Generative Modeling for Synthetic Human Dynamics
• A Generative Imputation Method for Multimodal Alzheimer's Disease Diagnosis
• Harnessing Input-Adaptive Inference for Efficient VLN
• TaoCache: Structure-Maintained Video Generation Acceleration
• How Does a Virtual Agent Decide Where to Look? -- Symbolic Cognitive Reasoning for Embodied Head Rotation
• DiffPhysCam: Differentiable Physics-Based Camera Simulation for Inverse Rendering and Embodied AI
• A Parametric Bi-Directional Curvature-Based Framework for Image Artifact Classification and Quantification
• Exploring Palette based Color Guidance in Diffusion Models
• Subjective and Objective Quality Assessment of Banding Artifacts on Compressed Videos
• MMIF-AMIN: Adaptive Loss-Driven Multi-Scale Invertible Dense Network for Multimodal Medical Image Fusion
• SelfHVD: Self-Supervised Handheld Video Deblurring
• Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer
• MuGa-VTON: Multi-Garment Virtual Try-On via Diffusion Transformers with Prompt Customization
• IPBA: Imperceptible Perturbation Backdoor Attack in Federated Self-Supervised Learning
• Reinforcement Learning for Large Model: A Survey
• Learned Regularization for Microwave Tomography
• UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models
• Sea-Undistort: A Dataset for Through-Water Image Restoration in High Resolution Airborne Bathymetric Mapping
• QuantEIT: Ultra-Lightweight Quantum-Assisted Inference for Chest Electrical Impedance Tomography
• Multi-view Normal and Distance Guidance Gaussian Splatting for Surface Reconstruction
• Undress to Redress: A Training-Free Framework for Virtual Try-On
• BadPromptFL: A Novel Backdoor Threat to Prompt-based Federated Learning in Multimodal Models
• OMGSR: You Only Need One Mid-timestep Guidance for Real-World Image Super-Resolution
• Decoupled Functional Evaluation of Autonomous Driving Models via Feature Map Quality Scoring
• Unsupervised Real-World Super-Resolution via Rectified Flow Degradation Modelling
• Similarity Matters: A Novel Depth-guided Network for Image Restoration and A New Dataset
• CMAMRNet: A Contextual Mask-Aware Network Enhancing Mural Restoration Through Comprehensive Mask Guidance
• 3DGS-VBench: A Comprehensive Video Quality Evaluation Benchmark for 3DGS Compression
• CycleDiff: Cycle Diffusion Models for Unpaired Image-to-image Translation
• RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video
• Application of Noise2Inverse and adaptation (Noise2Phase) to single‐mask x‐ray phase contrast micro‐computed tomography
• FVGen: Accelerating Novel-View Synthesis with Adversarial Video Diffusion Distillation
• FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields
• InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow
• Synthetic Data Generation for Emotional Depth Faces: Optimizing Conditional DCGANs via Genetic Algorithms in the Latent Space and Stabilizing Training with Knowledge Distillation
• WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction
• Task complexity shapes internal representations and robustness in neural networks
• HiFi-Mamba: Dual-Stream W-Laplacian Enhanced Mamba for High-Fidelity MRI Reconstruction
• Textual and Visual Guided Task Adaptation for Source-Free Cross-Domain Few-Shot Segmentation
• Generative Artificial Intelligence in Medical Imaging: Foundations, Progress, and Clinical Translation
• PoseGen: In-Context LoRA Finetuning for Pose-Controllable Long Human Video Generation
• FLUX-Makeup: High-Fidelity, Identity-Consistent, and Robust Makeup Transfer via Diffusion Transformer
• UGOD: Uncertainty-Guided Differentiable Opacity and Soft Dropout for Enhanced Sparse-View 3DGS
• Laplacian Analysis Meets Dynamics Modelling: Gaussian Splatting for 4D Reconstruction
• Perceive-Sample-Compress: Towards Real-Time 3D Gaussian Splatting
• FedMP: Tackling Medical Feature Heterogeneity in Federated Learning from a Manifold Perspective
• MZEN: Multi-Zoom Enhanced NeRF for 3-D Reconstruction with Unknown Camera Poses
• Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off
• RetinexDual: Retinex-based Dual Nature Approach for Generalized Ultra-High-Definition Image Restoration
• Combined Image Data Augmentations diminish the benefits of Adaptive Label Smoothing
• UniTalker: Conversational Speech-Visual Synthesis
• One Model for All: Unified Try-On and Try-Off in Any Pose via LLM-Inspired Bidirectional Tweedie Diffusion
• Two-Way Garment Transfer: Unified Diffusion Framework for Dressing and Undressing Synthesis
• QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution
• From Flat to Round: Redefining Brain Decoding with Surface-Based fMRI and Cortex Structure
• Dyna3DGR: 4D Cardiac Motion Tracking with Dynamic 3D Gaussian Representation
• PIS3R: Very Large Parallax Image Stitching via Deep 3D Reconstruction
• Uncertainty-Aware Spatial Color Correlation for Low-Light Image Enhancement
• DET-GS: Depth- and Edge-Aware Regularization for High-Fidelity 3D Gaussian Splatting
• Age-Diverse Deepfake Dataset: Bridging the Age Gap in Deepfake Detection
• Towards Globally Predictable k-Space Interpolation: A White-box Transformer Approach
• SPJFNet: Self-Mining Prior-Guided Joint Frequency Enhancement for Ultra-Efficient Dark Image Restoration
• CADD: Context aware disease deviations via restoration of brain images using normative conditional diffusion models
• EditGarment: An Instruction-Based Garment Editing Dataset Constructed with Automated MLLM Synthesis and Semantic-Aware Evaluation
• Diffusion Once and Done: Degradation-Aware LoRA for Efficient All-in-One Image Restoration
• CIVQLLIE: Causal Intervention with Vector Quantization for Low-Light Image Enhancement
• Beyond Illumination: Fine-Grained Detail Preservation in Extreme Dark Image Restoration
• Physics-Constrained Fine-Tuning of Flow-Matching Models for Generation and Inverse Problems
• BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models
• Duplex-GS: Proxy-Guided Weighted Blending for Real-Time Order-Independent Gaussian Splatting
• H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction
• RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions
• Low-rankness and Smoothness Meet Subspace: A Unified Tensor Regularization for Hyperspectral Image Super-resolution
• SA-3DGS: A Self-Adaptive Compression Method for 3D Gaussian Splatting
• ClinicalFMamba: Advancing Clinical Assessment using Mamba-based Multimodal Neuroimaging Fusion
• Managing Data for Scalable and Interactive Event Sequence Visualization
• Learning to Incentivize: LLM-Empowered Contract for AIGC Offloading in Teleoperation
• Evaluation of 3D Counterfactual Brain MRI Generation
• DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework
• From Pixels to Pathology: Restoration Diffusion for Diagnostic-Consistent Virtual IHC
• GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstruction
• Optimal Transport for Rectified Flow Image Editing: Unifying Inversion-Based and Direct Methods
• After the Party: Navigating the Mapping From Color to Ambient Lighting
• DeflareMamba: Hierarchical Vision Mamba for Contextually Consistent Lens Flare Removal
• QuaDreamer: Controllable Panoramic Video Generation for Quadruped Robots
• Frequency-Domain Denoising-Based in Vivo Fluorescence Imaging
• PMGS: Reconstruction of Projectile Motion Across Large Spatiotemporal Spans via 3D Gaussian Splatting
• Protego: User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint Exposure
• PoseGuard: Pose-Guided Generation with Safety Guardrails
• A Neural Quality Metric for BRDF Models
• Text2Lip: Progressive Lip-Synced Talking Face Generation from Text via Viseme-Guided Rendering
• PRIMU: Uncertainty Estimation for Novel Views in Gaussian Splatting from Primitive-Based Representations of Error and Coverage
• DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization
• Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systems
• Practical, Generalizable and Robust Backdoor Attacks on Text-to-Image Diffusion Models
• Physically-based Lighting Generation for Robotic Manipulation
• Integrating Disparity Confidence Estimation into Relative Depth Prior-Guided Unsupervised Stereo Matching
• OCSplats: Observation Completeness Quantification and Label Noise Separation in 3DGS
• MoGaFace: Momentum-Guided and Texture-Aware Gaussian Avatars for Consistent Facial Geometry
• No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
• Screencast-Based Analysis of User-Perceived GUI Responsiveness
• The Promise of RL for Autoregressive Image Editing
• MASIV: Toward Material-Agnostic System Identification from Videos
• DreamSat-2.0: Towards a General Single-View Asteroid 3D Reconstruction
• LeakyCLIP: Extracting Training Data from CLIP
• FW-VTON: Flattening-and-Warping for Person-to-Person Virtual Try-on
• CoProU-VO: Combining Projected Uncertainty for End-to-End Unsupervised Monocular Visual Odometry
• Video Color Grading via Look-Up Table Generation
• PIF-Net: Ill-Posed Prior Guided Multispectral and Hyperspectral Image Fusion via Invertible Mamba and Fusion-Aware LoRA
• IN2OUT: Fine-Tuning Video Inpainting Model for Video Outpainting Using Hierarchical Discriminator
• SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies
• Dream, Lift, Animate: From Single Images to Animatable Gaussian Avatars
• Exploring Fourier Prior and Event Collaboration for Low-Light Image Enhancement
• Sample-Aware Test-Time Adaptation for Medical Image-to-Image Translation
• Stereo 3D Gaussian Splatting SLAM for Outdoor Urban Scenes
• Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localization
• NeRF Is a Valuable Assistant for 3D Gaussian Splatting
• Who is a Better Talker: Subjective and Objective Quality Assessment for AI-Generated Talking Heads
• Towards Measuring and Modeling Geometric Structures in Time Series Forecasting via Image Modality
• EMORe: Motion-Robust 5D MRI Reconstruction via Expectation-Maximization-Guided Binning Correction and Outlier Rejection
• Adversarial-Guided Diffusion for Multimodal LLM Attacks
• LIVE-GS: Online LiDAR-Inertial-Visual State Estimation and Globally Consistent Mapping with 3D Gaussian Splatting
• BS-1-to-N: Diffusion-Based Environment-Aware Cross-BS Channel Knowledge Map Generation for Cell-Free Networks
• UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration
• FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning
• Towards High-Resolution Alignment and Super-Resolution of Multi-Sensor Satellite Imagery
• Ray-tracing image simulations of transparent objects with complex shape and inhomogeneous refractive index
• MRpro - open PyTorch-based MR reconstruction and processing package
• DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splatting
• Advancing Fetal Ultrasound Image Quality Assessment in Low-Resource Settings
• Gaussian Splatting with Discretized SDF for Relightable Assets
• Towards Blind Bitstream-corrupted Video Recovery via a Visual Foundation Model-driven Framework
• Moiré Zero: An Efficient and High-Performance Neural Architecture for Moiré Removal
• UFV-Splatter: Pose-Free Feed-Forward 3D Gaussian Splatting Adapted to Unfavorable Views
• LAMA-Net: A Convergent Network Architecture for Dual-Domain Reconstruction
• Trade-offs in Image Generation: How Do Different Dimensions Interact?
• SAIGFormer: A Spatially-Adaptive Illumination-Guided Network for Low-Light Image Enhancement
• Neural network enabled wide field-of-view imaging with hyperbolic metalenses
• Text-Aware Image Restoration with Diffusion Models
• Mask-Free Audio-driven Talking Face Generation for Enhanced Visual Quality and Identity Preservation
• Endoscopic Depth Estimation Based on Deep Learning: A Survey
• Compositional Video Synthesis by Temporal Object-Centric Learning
• Onboard Hyperspectral Super-Resolution with Deep Pushbroom Neural Network
• Benefits of Feature Extraction and Temporal Sequence Analysis for Video Frame Prediction: An Evaluation of Hybrid Deep Learning Models
• Towards trustworthy AI in materials mechanics through domain-guided attention
• Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution
• Harnessing Diffusion-Yielded Score Priors for Image Restoration
• Annotation-Free Human Sketch Quality Assessment
• WEEP: A Differentiable Nonconvex Sparse Regularizer via Weakly-Convex Envelope
• JWB-DH-V1: Benchmark for Joint Whole-Body Talking Avatar and Speech Generation Version 1
• ModalFormer: Multimodal Transformer for Low-Light Image Enhancement
• MagicAnime: A Hierarchically Annotated, Multimodal and Multitasking Dataset with Benchmarks for Cartoon Animation Generation
• EndoControlMag: Robust Endoscopic Vascular Motion Magnification with Periodic Reference Resetting and Hierarchical Tissue-aware Dual-Mask Control
• Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training
• Decomposing Densification in Gaussian Splatting for Faster 3D Scene Reconstruction
• GT-Mean Loss: A Simple Yet Effective Solution for Brightness Mismatch in Low-Light Image Enhancement
• SuperMag: Vision-based Tactile Data Guided High-resolution Tactile Shape Reconstruction for Magnetic Tactile Sensors
• CHADET: Cross-Hierarchical-Attention for Depth-Completion Using Unsupervised Lightweight Transformer
• A Generative Model for Disentangling Galaxy Photometric Parameters
• A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction
• Taking Language Embedded 3D Gaussian Splatting into the Wild
• ForCenNet: Foreground-Centric Network for Document Image Rectification
• MoFRR: Mixture of Diffusion Models for Face Retouching Restoration
• Tuning adaptive gamma correction (TAGC) for enhancing images in low ligh
• ChartM³: Benchmarking Chart Editing with Multimodal Instructions
• WACA-UNet: Weakness-Aware Channel Attention for Static IR Drop Prediction in Integrated Circuit Design
• DASH: 4D Hash Encoding with Self-Supervised Decomposition for Real-Time Dynamic Scene Rendering
• Cross-Subject Mind Decoding from Inaccurate Representations
• Fast Learning of Non-Cooperative Spacecraft 3D Models through Primitive Initialization
• Plug and Play Splitting Techniques for Poisson Image Restoration
• Dual Path Learning -- learning from noise and context for medical image denoising
• Learning Efficient and Generalizable Human Representation with Human Gaussian Model
• DRWKV: Focusing on Object Edges for Low-Light Image Enhancement
• Diffusion models for multivariate subsurface generation and efficient probabilistic inversion
• PS-GS: Gaussian Splatting for Multi-View Photometric Stereo
• GEDTM30: global ensemble digital terrain model at 30 m and derived multiscale terrain variables
• G2S-ICP SLAM: Geometry-aware Gaussian Splatting ICP SLAM
• U-Net Based Healthy 3D Brain Tissue Inpainting
• Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement
• Degradation-Consistent Learning via Bidirectional Diffusion for Low-Light Image Enhancement
• OmniVTON: Training-Free Universal Virtual Try-On
• Grounding Degradations in Natural Language for All-In-One Video Restoration
• SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion Models
• Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey
• VisGuard: Securing Visualization Dissemination through Tamper-Resistant Data Retrieval
• PCR-GS: COLMAP-Free 3D Gaussian Splatting via Pose Co-Regularizations
• InvRGB+L: Inverse Rendering of Complex Scenes with Unified Color and LiDAR Reflectance Modeling
• Accelerating Parallel Diffusion Model Serving with Residual Compression
• Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack
• Perceptual Classifiers: Detecting Generative Images using Perceptual Features
• Efficient Burst Super-Resolution with One-step Diffusion
• UNICE: Training A Universal Image Contrast Enhancer
• Vision Transformer attention alignment with human visual perception in aesthetic object evaluation
• Improving Multislice Electron Ptychography with a Generative Prior
• DFDNet: Dynamic Frequency-Guided De-Flare Network
• Tell Me Without Telling Me: Two-Way Prediction of Visualization Literacy and Visual Attention
• Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolution
• Sparse-View 3D Reconstruction: Recent Advances and Open Challenges
• M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision
• Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs
• HairShifter: Consistent and High-Fidelity Video Hair Transfer via Anchor-Guided Animation
• DeQA-Doc: Adapting DeQA-Score to Document Image Quality Assessment
• FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers
• Think-Before-Draw: Decomposing Emotion Semantics & Fine-Grained Controllable Expressive Talking Head Generation
• Multi-Component VAE with Gaussian Markov Random Field
• SmokeSVD: Smoke Reconstruction from A Single View via Progressive Novel View Synthesis and Refinement with Diffusion Models
• EC-Diff: Fast and High-Quality Edge-Cloud Collaborative Inference for Diffusion Models
• CompressedVQA-HDR: Generalized Full-reference and No-reference Quality Assessment Models for Compressed High Dynamic Range Videos
• Pathology-Guided Virtual Staining Metric for Evaluation and Training
• Wavelet-GS: 3D Gaussian Splatting with Wavelet Decomposition
• Generate to Ground: Multimodal Text Conditioning Boosts Phrase Grounding in Medical Vision-Language Models
• BRUM: Robust 3D Vehicle Reconstruction from 360 Sparse Images
• HPR3D: Hierarchical Proxy Representation for High-Fidelity 3D Reconstruction and Controllable Editing
• Interpretable Prediction of Lymph Node Metastasis in Rectal Cancer MRI Using Variational Autoencoders
• Elevating 3D Models: High-Quality Texture and Geometry Refinement from a Low-Quality Model
• Deep Equilibrium models for Poisson Imaging Inverse problems via Mirror Descent
• SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields
• SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping
• StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams
• HiSin: A Sinogram-Aware Framework for Efficient High-Resolution Inpainting
• Gaussian2Scene: 3D Scene Representation Learning via Self-supervised Learning with 3D Gaussian Splatting
• MFGDiffusion: Mask-Guided Smoke Synthesis for Enhanced Forest Fire Detection
• A Neural Network Model of Complementary Learning Systems: Pattern Separation and Completion for Continual Learning
• Physically Based Neural LiDAR Resimulation
• WaFusion: A Wavelet-Enhanced Diffusion Framework for Face Morph Generation
• Quantize-then-Rectify: Efficient VQ-VAE Training
• 3DGAA: Realistic and Robust 3D Gaussian-based Adversarial Attack for Autonomous Driving
• VoxelRF: Voxelized Radiance Field for Fast Wireless Channel Modeling
• Ambient Diffusion Omni: Training Good Models with Bad Data
• I2I-PR: Deep Iterative Refinement for Phase Retrieval using Image-to-Image Diffusion Models
• When Schrödinger Bridge Meets Real-World Image Dehazing with Unpaired Training
• RectifiedHR: High-Resolution Diffusion via Energy Profiling and Adaptive Guidance Scheduling
• AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learning
• Visual Surface Wave Elastography: Revealing Subsurface Physical Properties via Visible Surface Waves
• Physics-Aware Fluid Field Generation from User Sketches Using Helmholtz-Hodge Decomposition
• Generalizable 7T T1-map Synthesis from 1.5T and 3T T1 MRI with an Efficient Transformer Model
• Towards Imperceptible JPEG Image Hiding: Multi-range Representations-driven Adversarial Stego Generation
• M2DAO-Talker: Harmonizing Multi-granular Motion Decoupling and Alternating Optimization for Talking-head Generation
• RePaintGS: Reference-Guided Gaussian Splatting for Realistic and View-Consistent 3D Scene Inpainting
• D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping
• Occlusion-Aware Temporally Consistent Amodal Completion for 3D Human-Object Interaction Reconstruction
• Multigranular Evaluation for Brain Visual Decoding
• Dense Temporal Contrast Synthesis via Conditioned Latent Transport
• D-CNN and VQ-VAE Autoencoders for Compression and Denoising of Industrial X-ray Computed Tomography Images
• Stable-Hair v2: Real-World Hair Transfer via Multiple-View Diffusion Model
• Degradation-Agnostic Statistical Facial Feature Transformation for Blind Face Restoration in Adverse Weather Conditions
• EscherNet++: Simultaneous Amodal Completion and Scalable View Synthesis through Masked Fine-Tuning and Enhanced Feed-Forward 3D Reconstruction
• Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collections
• SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction
• Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
• ADIEE: Automatic Dataset Creation and Scorer for Instruction-Guided Image Editing Evaluation
• OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference
• A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality
• QR-Structured Thermal Triggers for Targeted Semantic Attacks on Infrared Vision-Language Models
• IAP: Invisible Adversarial Patch Attack through Perceptibility-Aware Localization and Perturbation Optimization
• Democratizing High-Fidelity Co-Speech Gesture Video Generation
• Residual Prior-driven Frequency-aware Network for Image Fusion
• FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting
• Capturing Stable HDR Videos Using a Dual-Camera System
• Deep Learning-based Human Gesture Channel Modeling for Integrated Sensing and Communication Scenarios
• Mask6D: Masked Pose Priors For 6D Object Pose Estimation
• HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancement
• Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
• FillGS: Filling Observation Gaps in 4D Gaussian Splatting via Viewpoint-Time Selection and Generative Refinement
• DreamArt: Generating Interactable Articulated Objects from a Single Image
• Resolving Extreme Data Scarcity by Explicit Physics Integration: An Application to Groundwater Heat Transport
• Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image Restoration
• Generative Panoramic Image Stitching
• D-FCGS: Feedforward Compression of Dynamic Gaussian Splatting for Free-Viewpoint Videos
• TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems
• SV-DRR: High-Fidelity Novel View X-Ray Synthesis Using Diffusion Model
• Semantic Frame Interpolation
• TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation
• SPIDER: Structure-Preferential Implicit Deep Network for Biplanar X-ray Reconstruction
• A Deep Unfolding Framework for Diffractive Snapshot Spectral Imaging
• Backdoors in Conditional Diffusion: Threats to Responsible Synthetic Data Pipelines
• Uncovering Neuroimaging Biomarkers of Brain Tumor Surgery with AI-Driven Methods
• Enhancing Underwater Images Using Deep Learning with Subjective Image Quality Integration
• GO-PRE: Goal-Oriented Next-Best-View Selection via Predictive Rendering Entropy for Active 3D Reconstruction
• A View-consistent Sampling Method for Regularized Training of Neural Radiance Fields
• Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers
• DMAT: An End-to-End Framework for Joint Atmospheric Turbulence Mitigation and Object Detection
• Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation
• Flux-Sculptor: Text-Driven Rich-Attribute Portrait Editing through Decomposed Spatial Flow Control
• Evaluating Adversarial Protections for Diffusion Personalization: A Comprehensive Study
• ArmGS: Composite Gaussian Appearance Refinement for Modeling Dynamic Urban Environments
• Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps
• PhotIQA: A photoacoustic image data set with image quality ratings
• Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
• A Fully Convolutional Approach to Denoising 2D Correlation Spectra
• Learning few-step posterior samplers by unfolding and distillation of diffusion models
• Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning
• VeFIA: An Efficient Inference Auditing Framework for Vertical Federated Collaborative Software
• DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation
• MAC-Lookup: Multi-Axis Conditional Lookup Model for Underwater Image Enhancement
• SurgVisAgent: Multimodal Agentic Model for Versatile Surgical Visual Enhancement
• Sparse-view irradiation processing volumetric additive manufacturing
• LongAnimation: Long Animation Generation with Dynamic Global-Local Memory
• I3DM: Implicit 3D-aware Memory Retrieval and Injection for Consistent Video Scene Generation
• ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation
• FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases
• AIGVE-MACS: Unified Multi-Aspect Commenting and Scoring Model for AI-Generated Video Evaluation
• LLM-based Realistic Safety-Critical Driving Video Generation
• A Multi-Centric Anthropomorphic 3D CT Phantom-Based Benchmark Dataset for Harmonization
• Rapid Salient Object Detection with Difference Convolutional Neural Networks
• Enabling Robust, Real-Time Verification of Vision-Based Navigation through View Synthesis
• EvRWKV: A Continuous Interactive RWKV Framework for Effective Event-Guided Low-Light Image Enhancement
• Privacy-Preserving Quantized Federated Learning with Diverse Precision
• UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions
• LOD-GS: Level-of-Detail-Sensitive 3D Gaussian Splatting for Detail Conserved Anti-Aliasing
• FreNBRDF: A Frequency-Rectified Neural Material Representation
• Parameter-aware high-fidelity microstructure generation using stable diffusion
• Training for X-Ray Vision: Amodal Segmentation, Amodal Content Completion, and View-Invariant Object Representation from Multi-Camera Video
• Just Noticeable Difference for Large Multimodal Models
• Geological Everything Model 3D: A Promptable Foundation Model for Unified and Zero-Shot Subsurface Understanding
• A Systematic Investigation on Deep Learning-Based Omnidirectional Image and Video Super-Resolution
• Enhancing Interpretability in Generative Modeling: Statistically Disentangled Latent Spaces Guided by Generative Factors in Scientific Datasets
• Controllable Reference Guided Diffusion with Local Global Fusion for Real World Remote Sensing Image Super Resolution
• Image Demoiréing Using Dual Camera Fusion on Mobile Phones
• PointSSIM: A novel low dimensional resolution invariant image-to-image comparison metric
• AttentionGS: Towards Initialization-Free 3D Gaussian Splatting via Structural Attention
• OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving
• GViT: Representing Images as Gaussians for Visual Recognition
• On the convergence of iterative regularization method assisted by the graph Laplacian with early stopping
• On the Resilience of Underwater Semantic Wireless Communications
• DiffFit: Disentangled Garment Warping and Texture Refinement for Virtual Try-On
• PixelBoost: Leveraging Brownian Motion for Realistic-Image Super-Resolution
• STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene
• CoreMark: Toward Robust and Universal Text Watermarking Technique
• From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting
• AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation
• Peccavi: Visual Paraphrase Attack Safe and Distortion Free Image Watermarking Technique for AI-Generated Images
• GamerAstra: Supporting 2D Non-Twitch Video Games for Blind and Low-Vision Players through a Multi-Agent Framework
• RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors
• ICME 2025 Generalizable HDR and SDR Video Quality Measurement Grand Challenge
• VSRM: A Robust Mamba-Based Framework for Video Super-Resolution
• Degradation-Modeled Multipath Diffusion for Tunable Metalens Photography
• UniFuse: A Unified All-in-One Framework for Multi-Modal Medical Image Fusion Under Diverse Degradations and Misalignments
• GameTileNet: A Semantic Dataset for Low-Resolution Game Art in Procedural Content Generation
• HazeMatching: Dehazing Light Microscopy Images with Guided Conditional Flow Matching
• Few-Shot Identity Adaptation for 3D Talking Heads via Global Gaussian Field
• Noise-Inspired Diffusion Model for Generalizable Low-Dose CT Reconstruction
• Evaluating Sound Similarity Metrics for Differentiable, Iterative Sound-Matching
• ZeroReg3D: A Zero-shot Registration Pipeline for 3D Consecutive Histopathology Image Reconstruction
• OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting
• MirrorMe: Towards Realtime and High Fidelity Audio-Driven Halfbody Animation
• Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration
• Uncover Treasures in DCT: Advancing JPEG Quality Enhancement by Exploiting Latent Correlations
• Mapping intratumoral heterogeneity through PET-derived washout and deep learning after proton therapy
• Learning to See in the Extremely Dark
• Video Virtual Try-on with Conditional Diffusion Transformer Inpainter
• DBMovi-GS: Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting
• Geometry and Perception Guided Gaussians for Multiview-consistent 3D Generation from a Single Image
• Electromagnetic Inverse Scattering from a Single Transmitter
• CitrusGAN: sparse-view X-ray CT reconstruction for citrus based on generative adversarial networks
• Fast ground penetrating radar dual-parameter full waveform inversion method accelerated by hybrid compilation of CUDA kernel function and PyTorch
• Generative Models at the Frontier of Compression: A Survey on Generative Face Video Coding
• Progressive Alignment Degradation Learning for Pansharpening
• SkinningGS: Editable Dynamic Human Scene Reconstruction Using Gaussian Splatting Based on a Skinning Model
• Photon Absorption Remote Sensing (PARS): Comprehensive Absorption Imaging Enabling Label-Free Biomolecule Characterization and Mapping
• RecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation
• Towards Efficient Exemplar Based Image Editing with Multimodal VLMs
• NeRF-based CBCT Reconstruction needs Normalization and Initialization
• Video Compression for Spatiotemporal Earth System Data
• Vision Transformer-Based Time-Series Image Reconstruction for Cloud-Filling Applications
• Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation
• Parametric Gaussian Human Model: Generalizable Prior for Efficient and Realistic Human Avatar Modeling
• A Comparative Study of NAFNet Baselines for Image Restoration
• Diffusion-aided Task-oriented Semantic Communications with Model Inversion Attack
• Style Transfer: A Decade Survey
• UniTac-NV: A Unified Tactile Representation For Non-Vision-Based Tactile Sensors
• ICP-3DGS: SfM-free 3D Gaussian Splatting for Large-scale Unbounded Scenes
• VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory
• 4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time
• Light of Normals: Unified Feature Representation for Universal Photometric Stereo
• TAMMs: Temporal-Aware Multimodal Model for Satellite Image Change Understanding and Forecasting
• ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs
• 3D Arena: An Open Platform for Generative 3D Evaluation
• R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
• VisualChef: Generating Visual Aids in Cooking via Mask Inpainting
• OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation
• Transforming H&E images into IHC: A Variance-Penalized GAN for Precision Oncology
• BSMamba: Brightness and Semantic Modeling for Long-Range Interaction in Low-Light Image Enhancement
• A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image Enhancement
• Limitations of NERF with pre-trained Vision Features for Few-Shot 3D Reconstruction
• NOVA3D: Normal Aligned Video Diffusion Model for Single Image to 3D Generation
• 4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos
• BPCLIP: A Bottom-up Image Quality Assessment from Distortion to Semantics Based on CLIP
• Adapting Vision-Language Models for Evaluating World Models
• EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric Observations
• StainPIDR: A Pathological Image Decouplingand Reconstruction Method for Stain Normalization Based on Color Vector Quantization and Structure Restaining
• StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets
• Robust Foreground-Background Separation for Severely-Degraded Videos Using Convolutional Sparse Representation Modeling
• 3D Gaussian Splatting for Fine-Detailed Surface Reconstruction in Large-Scale Scene
• MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization
• Reversing Flow for Image Restoration
• Visual-Instructed Degradation Diffusion for All-in-One Image Restoration
• Cross-modal Offset-guided Dynamic Alignment and Fusion for Weakly Aligned UAV Object Detection
• TeSG: Textual Semantic Guidance for Infrared and Visible Image Fusion
• RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought
• MetaQAP - A Meta-Learning Approach for Quality-Aware Pretraining in Image Quality Assessment
• Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control
• Generative Learning of Differentiable Object Models for Compositional Interpretation of Complex Scenes
• FFINO: Factorized Fourier Improved Neural Operator for Modeling Multiphase Flow in Underground Hydrogen Storage
• MoiréXNet: Adaptive Multi-Scale Demoiréing with Linear Attention Test-Time Training and Truncated Flow Matching Prior
• Active MRI Acquisition with Diffusion Guided Bayesian Experimental Design
• PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
• Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization
• NTIRE 2025 Image Shadow Removal Challenge Report
• One-shot Face Sketch Synthesis in the Wild via Generative Diffusion Prior and Instruction Tuning
• Aligning Text, Images, and 3D Structure Token-by-Token
• Fiber Signal Denoising Algorithm using Hybrid Deep Learning Networks
• You Only Render Once: Enhancing Energy and Computation Efficiency of Mobile Virtual Reality
• A Digital Twin Framework for Adaptive Treatment Planning in Radiotherapy
• ProSplat: Improved Feed-Forward 3D Gaussian Splatting for Wide-Baseline Sparse Views
• Causally Steered Diffusion for Automated Video Counterfactual Generation
• GrFormer: A Novel Transformer on Grassmann Manifold for Infrared and Visible Image Fusion
• DepthSeg: Depth prompting in remote sensing semantic segmentation
• Breaking the Multi-Enhancement Bottleneck: Domain-Consistent Quality Enhancement for Compressed Images
• Frequency-Calibrated Membership Inference Attacks on Medical Image Diffusion Models
• 3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting
• Exploring Diffusion with Test-Time Training on Efficient Image Restoration
• Latent Anomaly Detection: Masked VQ-GAN for Unsupervised Segmentation in Medical CBCT
• ESRPCB: an Edge guided Super-Resolution model and Ensemble learning for tiny Printed Circuit Board Defect detection
• SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer
• TextureSplat: Per-Primitive Texture Mapping for Reflective Gaussian Splatting
• Micro-macro Gaussian Splatting with Enhanced Scalability for Unconstrained Scene Reconstruction
• A Dual-Layer Image Encryption Framework Using Chaotic AES with Dynamic S-Boxes and Steganographic QR Codes
• Efficient multi-view training for 3D Gaussian Splatting
• Using Neurogram Similarity Index Measure (NSIM) to Model Hearing Loss and Cochlear Neural Degeneration
• Task-driven real-world super-resolution of document scans
• DM³Net: Dual-Camera Super-Resolution via Domain Modulation and Multi-scale Matching
• Learning Unpaired Image Dehazing with Physics-based Rehazy Generation
• Improved Iterative Refinement for Chart-to-Code Generation via Structured Instruction
• Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting
• Restoring Gaussian Blurred Face Images for Deanonymization Attacks
• Optimal Transport Driven Asymmetric Image-to-Image Translation for Nuclei Segmentation of Histological Images
• InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning
• Fine-Grained HDR Image Quality Assessment From Noticeably Distorted to Very High Fidelity
• Efficient Star Distillation Attention Network for Lightweight Image Super-Resolution
• Benchmarking Image Similarity Metrics for Novel View Synthesis Applications
• Diffusion-Based Electrocardiography Noise Quantification via Anomaly Detection
• Hi-VAE: Efficient Video Autoencoding with Global and Detailed Motion
• CGVQM+D: Computer Graphics Video Quality Metric and Dataset
• FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution
• Taming Stable Diffusion for Computed Tomography Blind Super-Resolution
• Multi-Step Guided Diffusion for Image Restoration on Edge Devices: Toward Lightweight Perception in Embodied AI
• SPLATART: Articulated Gaussian Splatting with Estimated Object Structure
• ICME 2025 Grand Challenge on Video Super-Resolution for Video Conferencing
• Voxel-Level Brain States Prediction Using Swin Transformer
• Auditing Data Provenance in Real-world Text-to-Image Diffusion Models for Privacy and Copyright Protection
• SiliCoN: Simultaneous Nuclei Segmentation and Color Normalization of Histological Images
• Gaussian Mapping for Evolving Scenes
• SlotPi: Physics-informed Object-centric Reasoning Models
• NSD-Imagery: A benchmark dataset for extending fMRI vision decoding methods to mental imagery
• Edit360: 2D Image Edits to 3D Assets from Any Angle
• PointGS: Point Attention-Aware Sparse View Synthesis with Gaussian Splatting
• DUN-SRE: Deep Unrolling Network with Spatiotemporal Rotation Equivariance for Dynamic MRI Reconstruction
• RealKeyMorph: Keypoints in Real-world Coordinates for Resolution-agnostic Image Registration
• Rethinking Brain Tumor Segmentation from the Frequency Domain Perspective
• Generalized Gaussian Entropy Model for Point Cloud Attribute Compression with Dynamic Likelihood Intervals
• FA-INR: Adaptive Implicit Neural Representations for Interpretable Exploration of Simulation Ensembles
• Splat and Replace: 3D Reconstruction with Repetitive Elements
• ChronoTailor: Harnessing Attention Guidance for Fine-Grained Video Virtual Try-On
• Reliable Evaluation of MRI Motion Correction: Dataset and Insights
• SurGSplat: Progressive Geometry-Constrained Gaussian Splatting for Surgical Scene Reconstruction
• BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading
• Optimization-Free Universal Watermark Forgery with Regenerative Diffusion Models
• DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation
• Bidirectional Image-Event Guided Fusion Framework for Low-Light Image Enhancement
• HAVIR: HierArchical Vision to Image Reconstruction using CLIP-Guided Versatile Diffusion
• GS4: Generalizable Sparse Splatting Semantic SLAM
• SSH-Net: A Self-Supervised and Hybrid Network for Noisy Image Watermark Removal
• MDE-Edit: Masked Dual-Editing for Multi-Object Image Editing via Diffusion Models
• Implicit Neural Representation-Based MRI Reconstruction Method with Sensitivity Map Constraints
• Latent Diffusion Model Based Denoising Receiver for 6G Semantic Communication: From Stochastic Differential Theory to Application
• Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution
• Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation
• FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion
• Defurnishing with X-Ray Vision: Joint Removal of Furniture from Panoramas and Mesh
• FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction
• Robustness as Architecture: Designing IQA Models to Withstand Adversarial Perturbations
• Enhancing Frequency for Single Image Super-Resolution with Learnable Separable Kernels
• Physics Informed Capsule Enhanced Variational AutoEncoder for Underwater Image Enhancement
• MDTD-ArtIR: Benchmarking Image Editing and Restoration Models for Art Image Restoration under Texture-Overlay Degradations
• UAV4D: Dynamic Neural Rendering of Human-Centric UAV Imagery using Gaussian Splatting
• Splatting Physical Scenes: End-to-End Real-to-Sim from Imperfect Robot Data
• Poisson Informed Retinex Network for Extreme Low-Light Image Enhancement
• GSsplat: Generalizable Semantic Gaussian Splatting for Novel-view Synthesis in 3D Scenes
• WDMamba: When Wavelet Degradation Prior Meets Vision Mamba for Image Dehazing
• RLMiniStyler: Light-weight RL Style Agent for Arbitrary Sequential Neural Style Generation
• Active Sampling for MRI-based Sequential Decision Making
• Tensor robust principal component analysis via the tensor nuclear over Frobenius norm
• SSIMBaD: Sigma Scaling with SSIM-Guided Balanced Diffusion for AnimeFace Colorization
• SplArt: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian Splatting
• Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting
• Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning
• Point Cloud Quality Assessment Using the Perceptual Clustering Weighted Graph (PCW-Graph) and Attention Fusion Network
• Res-MoCoDiff: Residual-guided diffusion models for motion artifact correction in brain MRI
• HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers
• Solving Inverse Problems with FLAIR
• ControlMambaIR: Conditional Controls with State-Space Model for Image Restoration
• ORV: 4D Occupancy-centric Robot Video Generation
• SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation
• PhysGaia: A Physics-Aware Benchmark with Multi-Body Interactions for Dynamic Novel View Synthesis
• VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians
• RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers
• A Tree-guided CNN for image super-resolution
• LinkTo-Anime: A 2D Animation Optical Flow Dataset from 3D Model Rendering
• Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment
• Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control
• DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systems
• Playing with Transformer at 30+ FPS via Next-Frame Diffusion
• Ultra-High-Resolution Image Synthesis: Data, Method and Evaluation
• E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models
• NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challenge
• DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing
• Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction?
• MedEBench: Diagnosing Reliability in Text-Guided Medical Image Editing
• AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation
• Globally Consistent RGB-D SLAM with 2D Gaussian Splatting
• Multiverse Through Deepfakes: The MultiFakeVerse Dataset of Person-Centric Visual and Conceptual Manipulations
• MoCA-Video: Motion-Aware Concept Alignment for Consistent Video Editing
• Video Signature: Implicit Watermarking for Video Diffusion Models
• ViVo: A Dataset for Volumetric Video Reconstruction and Compression
• Real-Time Person Image Synthesis Using a Flow Matching Model
• Revolutionizing Brain Tumor Imaging: Generating Synthetic 3D FA Maps from T1-Weighted MRI using CycleGAN Models
• SEED: A Benchmark Dataset for Sequential Facial Attribute Editing with Diffusion Models
• CXR-AD: Component X-ray Image Dataset for Industrial Anomaly Detection
• Beyond Pretty Pictures: Combined Single- and Multi-Image Super-resolution for Sentinel-2 Images
• DreamDance: Animating Character Art via Inpainting Stable Gaussian Worlds
• Co-designed pre-capture privacy optics for computer vision
• 3D Gaussian Splatting Data Compression with Mixture of Priors
• Digital twins enable full-reference quality assessment of photoacoustic image reconstructions
• IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models
• A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancement
• Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction
• VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL
• Cora: Correspondence-aware image editing using few step diffusion
• AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
• LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter
• VITON-DRR: Details Retention Virtual Try-on via Non-rigid Registration
• PAN-Crafter: Learning Modality-Consistent Alignment for PAN-Sharpening
• Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis
• Quality assessment of 3D human animation: Subjective and objective evaluation
• Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting
• Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey
• FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
• MMGT: Motion Mask Guided Two-Stage Network for Co-Speech Gesture Video Generation
• Zero-P-to-3: Zero-Shot Partial-View Images to 3D Object
• SeG-SR: Integrating Semantic Knowledge into Remote Sensing Image Super-Resolution via Vision-Language Model
• HyperMotion: DiT-Based Pose-Guided Human Image Animation of Complex Motions
• Super-temporal-resolution Photoacoustic Imaging with Dynamic Reconstruction through Implicit Neural Representation in Sparse-view
• DeepTopoNet: A Framework for Subglacial Topography Estimation on the Greenland Ice Sheets
• Semantics-Guided Generative Image Compression
• ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS
• On a novel probabilistic Sampling Kantorovich operators and their application
• UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes
• Anomalies by Synthesis: Anomaly Detection using Generative Diffusion Models for Off-Road Navigation
• PALADIN : Robust Neural Fingerprinting for Text-to-Image Diffusion Models
• Understanding Adversarial Training with Energy-based Models
• GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control
• UP-SLAM: Adaptively Structured Gaussian SLAM with Uncertainty Prediction in Dynamic Environments
• FaceEditTalker: Controllable Talking Head Generation with Facial Attribute Editing
• LatentMove: Towards Complex Human Movement Video Generation
• GL-PGENet: A Parameterized Generation Framework for Robust Document Image Enhancement
• VRAG: Learning World Models for Interactive Video Generation
• STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering
• Learning Hierarchical Sparse Transform Coding for 3DGS Compression
• How Do Diffusion Models Improve Adversarial Robustness?
• Deep Learning Empowered Sub-Diffraction Terahertz Backpropagation Single-Pixel Imaging
• Improving Brain-to-Image Reconstruction via Fine-Grained Text Bridging
• VideoMarkBench: Benchmarking Robustness of Video Watermarking
• Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model
• Sampling Kantorovich operators for speckle noise reduction using a Down-Up scaling approach and gap filling in remote sensing images
• Instance Data Condensation for Image Super-Resolution
• Assessing the Use of Face Swapping Methods as Face Anonymizers in Videos
• Wideband RF Radiance Field Modeling Using Frequency-embedded 3D Gaussian Splatting
• Entropy-Guided Sampling of Flat Modes in Discrete Spaces
• InstGenIE: Generative Image Editing Made Efficient with Mask-aware Caching and Scheduling
• Video Quality Monitoring for Remote Autonomous Vehicle Control
• Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals
• Structure from Collision
• Plenodium: UnderWater 3D Scene Reconstruction with Plenoptic Medium Representation
• DiMoSR: Feature Modulation via Multi-Branch Dilated Convolutions for Efficient Image Super-Resolution
• MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation
• Dynamic Vision from EEG Brain Recordings, How much does EEG know?
• Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting
• Music Source Restoration
• HaloGS: Loose Coupling of Compact Geometry and Gaussian Splats for 3D Scenes
• Long-Context State-Space Video World Models
• Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction
• Learning 3D Persistent Embodied World Models
• Structure Disruption: Subverting Malicious Diffusion-Based Inpainting via Self-Attention Query Perturbation
• VTBench: Comprehensive Benchmark Suite Towards Real-World Virtual Try-on Models
• Underwater Diffusion Attention Network with Contrastive Language-Image Joint Learning for Underwater Image Enhancement
• HF-VTON: High-Fidelity Virtual Try-On via Consistent Geometric and Semantic Alignment
• DeepInverse: A Python package for solving imaging inverse problems with deep learning
• OB3D: A New Dataset for Benchmarking Omnidirectional 3D Reconstruction Using Blender
• GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis
• ImgEdit: A Unified Image Editing Dataset and Benchmark
• Improving Novel view synthesis of 360^∘ Scenes in Extremely Sparse Views by Jointly Training Hemisphere Sampled Synthetic Images
• Deep learning of personalized priors from past MRI scans enables fast, quality-enhanced point-of-care MRI with low-cost systems
• Sparfels: Fast Reconstruction from Sparse Unposed Imagery
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition
• MMP-2K: A Benchmark Multi-Labeled Macro Photography Image Quality Assessment Database
• Querying Kernel Methods Suffices for Reconstructing their Training Data
• Geometry-guided Online 3D Video Synthesis with Multi-View Temporal Consistency
• MIND-Edit: MLLM Insight-Driven Editing via Language-Vision Projection
• SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation
• Veta-GS: View-dependent deformable 3D Gaussian Splatting for thermal infrared Novel-view Synthesis
• Eye-See-You: Reverse Pass-Through VR and Head Avatars
• CTRL-GS: Cascaded Temporal Residue Learning for 4D Gaussian Splatting
• Beyond Illumination: A Conditional Mutual Information-Guided Network for Low-Light Image Enhancement
• F-ANcGAN: An Attention-Enhanced Cycle Consistent Generative Adversarial Architecture for Synthetic Image Generation of Nanoparticles
• Towards more transferable adversarial attack in black-box manner
• DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation
• Detail Continuation over a Trustworthy Coarse Scale for Autoregressive Super-Resolution
• A Unified and Fast-Sampling Diffusion Bridge Framework via Stochastic Optimal Control
• SplatCo: Structure-View Collaborative Gaussian Splatting for Detail-Preserving Rendering of Large-Scale Unbounded Scenes
• DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learning
• UniqueSplat: View-Conditioned 3D Gaussian Splatting for Generalizable 3D Reconstruction
• Ownership Verification of DNN Models Using White-Box Adversarial Attacks with Specified Probability Manipulation
• Deblending Overlapping Galaxies in DECaLS Using Transformer-Based Algorithm: A Method Combining Multiple Bands and Data Types
• Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM
• TokBench: Evaluating Your Visual Tokenizer before Visual Generation
• High-Fidelity Functional Ultrasound Reconstruction via A Visual Auto-Regressive Framework
• Render-FM: A Foundation Model for Real-time Photorealistic Volumetric Rendering
• Loop-Mamba: A Loop Mamba with Degradation-Aware and Shared Memory for Old Photo Restoration
• Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency
• Seeing through Satellite Images at Street Views
• T²exture: Sparsely Perturbed Thermal-to-Texture Imaging
• Forward-only Diffusion Probabilistic Models
• On the use of Graphs for Satellite Image Time Series
• Disagree to Accelerate: Closing the Loop on Diffusion Feature Forecasts
• Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restoration
• Foresight Diffusion: Improving Sampling Consistency in Predictive Diffusion Models
• SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models
• DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution
• Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey
• Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction
• Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On
• TRAIL: Transferable Robust Adversarial Images via Latent diffusion
• Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction
• Accelerating Targeted Hard-Label Adversarial Attacks in Low-Query Black-Box Settings
• Masked Conditioning for Deep Generative Models
• Proxy Avatar Meets Low-Rank Caching: Real-Time One-Shot Emotion-Controllable Portrait Animation
• CP-LLM: Context and Pixel Aware Large Language Model for Video Quality Assessment
• EVA: Expressive Virtual Avatars from Multi-view Videos
• FRN: Fractal-Based Recursive Spectral Reconstruction Network
• R3GS: Gaussian Splatting for Robust Reconstruction and Relocalization in Unconstrained Image Collections
• GT2-GS: Geometry-aware Texture Transfer for Gaussian Splatting
• A Deep Learning Framework for Two-Dimensional, Multi-Frequency Propagation Factor Estimation
• My Face Is Mine, Not Yours: Facial Protection Against Diffusion Model Face Swapping
• MIEScore: Human-Aligned Evaluation for Multi-Source Image Editing
• X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography
• Bidirectional Variational Autoencoders
• StreamSplat: Streaming Feed-Forward 3D Gaussian Splatting
• MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models
• GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation
• Securing Transfer-Learned Networks with Reverse Homomorphic Encryption
• UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache
• RLVR-World: Training World Models with Reinforcement Learning
• Vid2World: Crafting Video Diffusion Models to Interactive World Models
• Enhancing Vision Transformer Explainability Using Artificial Astrocytes
• VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank
• Scan, Materialize, Simulate: A Generalizable Framework for Physically Grounded Robot Planning
• Towards Generating Realistic Underwater Images
• Exploring Image Quality Assessment from a New Perspective: Pupil Size
• Memory-Centric Embodied Question Answering
• RETRO: REthinking Tactile Representation Learning with Material PriOrs
• IPENS:Interactive Unsupervised Framework for Rapid Plant Phenotyping Extraction via NeRF-SAM2 Fusion
• Anti-Inpainting: A Proactive Defense Approach against Malicious Diffusion-based Inpainters under Unknown Conditions
• Towards a Universal Image Degradation Model via Content-Degradation Disentanglement
• Single Image Reflection Separation via Dual Prior Interaction Transformer
• Learning Driven Elastic Task Multi-Connectivity Immersive Computing Systems
• Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking
• Neural-Enhanced Rate Adaptation and Computation Distribution for Emerging mmWave Multi-User 3D Video Streaming Systems
• FreqSelect: Frequency-Aware fMRI-to-Image Reconstruction
• Context-Aware Autoregressive Models for Multi-Conditional Image Generation
• PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement
• Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
• CompBench: Benchmarking Complex Instruction-guided Image Editing
• Generative Adversarial Reconstruction with Adaptive Thresholding for Obstructed Targets in Computational Microwave Imaging
• VoiceCloak: A Multi-Dimensional Defense Framework against Unauthorized Diffusion-based Voice Cloning
• Accelerating Diffusion-based Super-Resolution with Dynamic Time-Spatial Sampling
• Black-box Adversaries from Latent Space: Unnoticeable Attacks on Human Pose and Shape Estimation
• MiniWorld: Democratizing the Training of Video World Models from Scratch
• NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results
• GTR: Gaussian Splatting Tracking and Reconstruction of Unknown Objects Based on Appearance and Geometric Complexity
• Ranking Image Fusion the Way Humans Do: A Learned Pairwise Preference Metric for Infrared-Visible Fusion Assessment
• Urban Representation Learning for Fine-grained Economic Mapping: A Semi-supervised Graph-based Approach
• From Fibers to Cells: Fourier-Based Registration Enables Virtual Cresyl Violet Staining From 3D Polarized Light Imaging
• Controlling spatial correlation in k-space interpolation networks for MRI reconstruction: denoising versus apparent blurring
• CleanPatrick: A Benchmark for Image Data Cleaning
• Hybrid-Domain Posterior Sampling for Inverse Problems via Latent Flow Matching
• Textured mesh Quality Assessment using Geometry and Color Field Similarity
• X2C: A Dataset Featuring Nuanced Facial Expressions for Realistic Humanoid Imitation
• QVGen: Pushing the Limit of Quantized Video Generative Models
• X-Edit: Detecting and Localizing Edits in Images Altered by Text-Guided Diffusion Models
• AeroLLE: Constrained Pseudo-Supervision for Nighttime Aerial Image Enhancement with the AeroNight-1.5K Benchmark
• Equal is Not Always Fair: A New Perspective on Hyperspectral Representation Non-Uniformity
• UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights
• What's Inside Your Diffusion Model? A Score-Based Riemannian Metric to Explore the Data Manifold
• A Physics-Informed Spatiotemporal Deep Learning Framework for Turbulent Systems
• ControlGS: Consistent Structural Compression Control for Deployment-Aware Gaussian Splatting
• MFogHub: Bridging Multi-Regional and Multi-Satellite Data for Global Marine Fog Detection and Forecasting
• MTVCrafter: 4D Motion Tokenization for Open-World Human Image Animation
• UICopilot: Automating UI Synthesis via Hierarchical Code Generation from Webpage Designs
• From Preimage Search To Source-Grounded Feature Inversion
• Learned Lightweight Smartphone ISP with Unpaired Data
• Large-Scale Gaussian Splatting SLAM
• FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation
• RainPro-8: An Efficient Deep Learning Model to Estimate Rainfall Probabilities Over 8 Hours
• Don't Forget your Inverse DDIM for Image Editing
• RPL-UIE: Reliable Prior Learning for Underwater Image Enhancement
• Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation
• An Exploration of Default Images in Text-to-Image Generation
• Meta-learning Slice-to-Volume Reconstruction in Fetal Brain MRI using Implicit Neural Representations
• FDIR: Harmonizing Fidelity and Human-Machine Preference in Lossy Compression Image Restoration
• Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis
• Sparse Point Cloud Patches Rendering via Splitting 2D Gaussians
• Video Models as Native 4D Renderers: World-Grounded Conditioning from Animated Mesh
• SymNet: A Multi-Task Network for Joint Radio Map Reconstruction and Transmitter Localization
• Beyond Edge Maps: Wavelet-Domain Conditioning for Multi-Adapter Map-to-Satellite Diffusion
• ACT-R: Adaptive Camera Trajectories for Single View 3D Reconstruction
• ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction
• Highly Undersampled MRI Reconstruction via a Single Posterior Sampling of Diffusion Models
• WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networks
• Beyond Consistency: Preserving Temporal Structure in Zero-Shot Video Editing
• PtyRAD: A High-performance and Flexible Ptychographic Reconstruction Framework with Automatic Differentiation
• Enabling Privacy-Aware AI-Based Ergonomic Analysis
• MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges
• Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning
• TUGS: Physics-based Compact Representation of Underwater Scenes by Tensorized Gaussian
• High-Frequency Prior-Driven Adaptive Masking for Accelerating Image Super-Resolution
• Enhancing Monocular Height Estimation via Sparse LiDAR-Guided Correction
• Fast and low energy approximate full adder based on FELIX logic
• DP-TRAE: A Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protection
• Joint Low-level and High-level Textual Representation Learning with Multiple Masking Strategies
• NeuGen: Amplifying the 'Neural' in Neural Radiance Fields for Domain Generalization
• MultiTaskVIF: Segmentation-oriented visible and infrared image fusion via multi-task learning
• PC-SRGAN: Physically Consistent Super-Resolution Generative Adversarial Network for General Transient Simulations
• ProFashion: Prototype-guided Fashion Video Generation with Multiple Reference Images
• Distributionally Robust Contract Theory for Edge AIGC Services in Teleoperation
• A review of advancements in low-light image enhancement using deep learning
• MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model
• Document Image Rectification Bases on Self-Adaptive Multitask Fusion
• TopicVD: A Topic-Based Dataset of Video-Guided Multimodal Machine Translation for Documentaries
• Towards order of magnitude X-ray dose reduction in breast cancer imaging using phase contrast and deep denoising
• A New k-Space Model for Non-Cartesian Fourier Imaging
• SVAD: From Single Image to 3D Avatar via Synthetic Data Generation with Video Diffusion and Data Augmentation
• D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation
• ItDPDM: Information-Theoretic Discrete Poisson Diffusion Model
• UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound Volumes
• Learning Heterogeneous Mixture of Scene Experts for Large-scale Neural Radiance Fields
• SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splatting
• HiLLIE: Human-in-the-Loop Training for Low-Light Image Enhancement
• Hybrid Image Resolution Quality Metric (HIRQM):A Comprehensive Perceptual Image Quality Assessment Framework
• Discrete Spatial Diffusion: Intensity-Preserving Diffusion Modeling
• PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth
• Priorconditioned Sparsity-Promoting Projection Methods for Deterministic and Bayesian Linear Inverse Problems
• GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels
• StereoVGGT: A Training-Free Visual Geometry Transformer for Stereo Vision
• FalconWing: An Ultra-Light Indoor Fixed-Wing UAV Platform for Vision-Based Autonomy
• CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering
• High Dynamic Range Novel View Synthesis with Single Exposure
• VRS-UIE: Value-Driven Reordering Scanning for Underwater Image Enhancement
• AdvSplat: Adversarial Attacks on Feed-Forward Gaussian Splatting Models
• Exact Posterior Score Estimation for Solving Linear Inverse Problems
• Generating Synthetic Wildlife Health Data from Camera Trap Imagery: A Pipeline for Alopecia and Body Condition Training Data
• MoECa: Aligning Feature Reuse with Expert Decomposition in Diffusion Transformers
• The Latent Color Subspace: Emergent Order in High-Dimensional Chaos
• An unsupervised GNN-transformer model for gold geochemical anomaly detection
• Tailor Made Embeddings for Quantum Machine Learning
• Unified Geometry-Guided ML-FTLE for Tracking Transient Chaos from Scalar Time Series
• InstructAttribute: Fine-grained Object Attributes editing with Instruction
• Towards Robust and Generalizable Gerchberg Saxton based Physics Inspired Neural Networks for Computer Generated Holography: A Sensitivity Analysis Framework
• Direct Motion Models for Assessing Generated Videos
• Optimized Lattice-Structured Flexible EIT Sensor for Tactile Reconstruction and Classification
• Combating Falsification of Speech Videos with Live Optical Signatures (Extended Version)
• Self-Aware Object Detection via Degradation Manifolds
• Unpaired Image-to-Image Translation via a Self-Supervised Semantic Bridge
• Benchmarking quantum simulation with neutron-scattering experiments
• GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
• Self-Supervised Monocular Visual Drone Model Identification through Improved Occlusion Handling
• Diffusion-based Adversarial Identity Manipulation for Facial Privacy Protection
• Revisiting Diffusion Autoencoder Training for Image Reconstruction Quality
• DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration
• Synergy-CLIP: Extending CLIP with Multi-modal Integration for Robust Representation Learning
• MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance
• ReVision: Refining Video Diffusion with Explicit 3D Motion Modeling
• RT-Splatting: Joint Reflection-Transmission Modeling with Gaussian Splatting
• MIRAGE: Robust multi-modal architectures translate fMRI-to-image models from vision to mental imagery
• Unconstrained Large-scale 3D Reconstruction and Rendering across Altitudes
• EfficientHuman: Efficient Training and Reconstruction of Moving Human using Articulated 2D Gaussian
• LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment: Methods and Results
• Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
• Unveiling the Underwater World: CLIP Perception Model-Guided Underwater Image Enhancement
• Perception-aware Sampling for Scatterplot Visualizations
• Legilimens: Performant Video Analytics on the System-on-Chip Edge
• TriniMark: A Robust Generative Speech Watermarking Method for Trinity-Level Traceability
• FreBIS: Frequency-Based Stratification for Neural Implicit Surface Representations
• CompleteMe: Reference-based Human Image Completion
• Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video
• Interactive Double Deep Q-network: Integrating Human Interventions and Evaluative Predictions in Reinforcement Learning of Autonomous Driving
• Masked Language Prompting for Generative Data Augmentation in Few-shot Fashion Style Recognition
• Signal or Noise? Understanding Generative Models for Real-World Sensor Time Series
• World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
• AnimateAnywhere: Rouse the Background in Human Image Animation
• Memento: Augmenting Personalized Memory via Practical Multimodal Wearable Sensing in Visual Search and Wayfinding Navigation
• FusionNet: Multi-model Linear Fusion Framework for Low-light Image Enhancement
• Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
• Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image
• RadioFormer: A Multiple-Granularity Radio Map Estimation Transformer with 1\textpertenthousand Spatial Sampling
• REED-VAE: RE-Encode Decode Training for Iterative Image Editing with Diffusion Models
• 4DGS-CC: A Contextual Coding Framework for 4D Gaussian Splatting Data Compression
• Augmenting Perceptual Super-Resolution via Image Quality Predictors
• Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
• Depth3DLane: Monocular 3D Lane Detection via Depth Prior Distillation
• Outlier-aware Tensor Robust Principal Component Analysis with Self-guided Data Augmentation
• Adaptive Weight Modified Riesz Mean Filter For High-Density Salt and Pepper Noise Removal
• Physics-Driven Neural Compensation For Electrical Impedance Tomography
• DiffMI: Breaking Face Recognition Privacy via Diffusion-Driven Training-Free Model Inversion
• HepatoGEN: Generating Hepatobiliary Phase MRI with Perceptual and Adversarial Models
• Latent-Compressed Variational Autoencoder for Video Diffusion Models
• Commodity RF Sensing of Belowground Tuber Growth
• Scene Perceived Image Perceptual Score (SPIPS): combining global and local perception for image quality assessment
• SDiT: Semantic Region-Adaptive for Diffusion Transformers
• Multi-modal MRI-Based Alzheimer's Disease Diagnosis with Transformer-based Image Synthesis and Transfer Learning
• FaithIR: Rethinking Infrared Image Super-Resolution from Perceptual Sharpness to Task Relevant Fidelity
• S³-Diff: Structural Semantic Synergy Diffusion Model for High Fidelity Super Resolution of Pathological Images
• Morphology-Aware Implicit Super-Resolution Network for Pathological Images
• XiDepth: a Lightweight and Efficient Network for Self-supervised Monocular Depth Estimation
• FlowForm: Synergizing Fluid Physics with Topological Consistency for Satellite Flood Synthesis
• UniNav: A Unified World-Action Diffusion Model for Visual Navigation
• NanoMorph-3D: An End-to-End Physics-Driven Unrolling Framework for Nanomaterial Reconstruction
• I-INR: Iterative Implicit Neural Representations
• 3DV-TON: Textured 3D-Guided Consistent Video Try-on via Diffusion Models
• STP4D: Spatio-Temporal-Prompt Consistent Modeling for Text-to-4D Gaussian Splatting
• LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning
• DCT-Shield: A Robust Frequency Domain Defense against Malicious Image Editing
• Deep Reparameterization for Full Waveform Inversion: Architecture Benchmarking, Robust Inversion, and Multiphysics Extension
• ScoreField: Neural Inverse Scattering with Score-Based Generative Priors
• Self-Supervised Noise Adaptive MRI Denoising via Repetition to Repetition (Rep2Rep) Learning
• Unveiling Hidden Vulnerabilities in Digital Human Generation via Adversarial Attacks
• Enhancing Variational Autoencoders with Smooth Robust Latent Encoding
• Casual3DHDR: Deblurring High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos
• High-Quality Cloud-Free Optical Image Synthesis Using Multi-Temporal SAR and Contaminated Optical Data
• UBLLIE: Unified Backlight and Low-Light Image Enhancement
• DAC-Pose: Dual-Agent Collaborative Framework for Pose-Guided Human Generation
• Overcoming Statistical Bias in Action-Controllable World Models
• ACA-GS: Adaptive-Capacity Anchored Gaussian Splatting for Compact Dynamic Radiance Fields
• Variable Smoothing for Weakly Convex Problems with Non-Euclidean Directions
• An active-learning framework for real-time depth perception from monocular vision streams
• A geometry-based deep equilibrium model for image restoration under multiplicative Gamma noise
• Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning
• Multi-View Face and Gesture Animation with Dynamic Gaussians
• OmniEdit-Bench: A Comprehensive Benchmark for Instruction-based Video Editing
• OmniVR: Joint Video-Audio Conditional Generation for Restoring Degraded Historical Films
• DeclutterNeRF: Generative-Free 3D Scene Recovery for Occlusion Removal
• Subjective Visual Quality Assessment for High-Fidelity Learning-Based Image Compression
• A Machine Learning and Finite Element Framework for Inverse Elliptic PDEs via Dirichlet-to-Neumann Mapping
• MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors
• SCAIL-2: Unifying Controlled Character Animation with End-to-End In-Context Conditioning
• Neural electron backscatter diffraction
• IConFace: Fine-Grained Identity Conditioning for Reference-Aware Face Restoration
• Image Thresholding: Understanding Bias of Evaluation Metrics Towards Specific Evaluation Functions
• From Understanding to Erasing: Towards Complete and Stable Video Object Removal
• Investigating How the Fractions Skill Score and Brier Divergence Skill Score Reflect Forecast Error
• TactileNet: Bridging the Accessibility Gap with AI-Generated Tactile Graphics for Individuals with Vision Impairment
• Texture2LoD3: Enabling LoD3 Building Reconstruction With Panoramic Images
• ECGDeDRDNet: A deep learning-based method for Electrocardiogram noise removal using a double recurrent dense network
• Targetless LiDAR-Camera Calibration with Neural Gaussian Splatting
• SaENeRF: Suppressing Artifacts in Event-based Neural Radiance Fields
• Iterative Collaboration Network Guided By Reconstruction Prior for Medical Image Super-Resolution
• Self-Guided Diffusion Model for Accelerating Computational Fluid Dynamics
• FluentLip: A Phonemes-Based Two-stage Approach for Audio-Driven Lip Synthesis with Optical Flow Consistency
• DSDNet: Raw Domain Demoiréing via Dual Color-Space Synergy
• StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussians
• DSPO: Direct Semantic Preference Optimization for Real-World Image Super-Resolution
• MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video
• Structure-guided Diffusion Transformer for Low-Light Image Enhancement
• SOLIDO: A Robust Watermarking Method for Speech Synthesis via Low-Rank Adaptation
• A Controllable Appearance Representation for Flexible Transfer and Editing
• NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Study
• Protecting Your Voice: Temporal-aware Robust Watermarking
• IXGS-Intraoperative 3D Reconstruction from Sparse, Arbitrarily Posed Real X-rays
• Frequency-domain Learning with Kernel Prior for Blind Image Deblurring
• NeRFlex: Resource-aware Real-time High-quality Rendering of Complex Scenes on Mobile Devices
• VGNC: Reducing the Overfitting of Sparse-view 3DGS via Validation-guided Gaussian Number Control
• FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models
• Metamon-GS: Enhancing Representability with Variance-Guided Densification and Light Encoding
• SEGA: Drivable 3D Gaussian Head Avatar from a Single Image
• RadioDiff-Inverse: Diffusion Enhanced Bayesian Inverse Estimation for ISAC Radio Map Construction
• Single Document Image Highlight Removal via A Large-Scale Real-World Dataset and A Location-Aware Network
• Fashion-RAG: Multimodal Fashion Image Editing via Retrieval-Augmented Generation
• Fragile Watermarking for Image Certification Using Deep Steganographic Embedding
• SLAM&Render: A Benchmark for the Intersection Between Neural Rendering, Gaussian Splatting and SLAM
• SupResDiffGAN a new approach for the Super-Resolution task
• EG-Gaussian: Epipolar Geometry and Graph Network Enhanced 3D Gaussian Splatting
• Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing
• Volume Encoding Gaussians: Transfer Function-Agnostic 3D Gaussians for Volume Rendering
• MGT: Extending Virtual Try-Off to Multi-Garment Scenarios
• CompGS++: Compressed Gaussian Splatting for Static and Dynamic Scene Representation
• Second-order Optimization of Gaussian Splats with Importance Sampling
• DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion
• A Survey on Cross-Modal Interaction Between Music and Multimodal Data
• NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
• UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models
• AdaQual-Diff: Diffusion-Based Image Restoration via Adaptive Quality Prompting
• High-Fidelity Image Inpainting with Multimodal Guided GAN Inversion
• Imaging for All-Day Wearable Smart Glasses
• TTRD3: Texture Transfer Residual Denoising Dual Diffusion Model for Remote Sensing Image Super-Resolution
• Digital Twin Generation from Visual Data: A Survey
• AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
• Event Quality Score (EQS): Assessing the Realism of Simulated Event Camera Streams via Distances in Latent Space
• Cobra: Efficient Line Art COlorization with BRoAder References
• Towards Realistic Low-Light Image Enhancement via ISP Driven Data Modeling
• Wavelet-based Variational Autoencoders for High-Resolution Image Generation
• PCDiff: Proactive Control for Ownership Protection in Diffusion Models with Watermark Compatibility
• 3R-GS: Best Practice in Optimizing Camera Poses Along with 3DGS
• NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results
• VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate
• EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos
• An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World
• HyperKING: Quantum-Classical Generative Adversarial Networks for Hyperspectral Image Restoration
• SafeDivertor: Faithful Divertor Heat Flux Reconstruction from Macroscopic Plasma State Signals via Time-Frequency Prior Exploitation
• Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping
• Equipment-centric workpiece localization in near real-time using deep learning-based vision and event-driven finite state machines
• LiteKD-Net: Lightweight Knowledge-Distilled Network for Mobile Image Denoising
• Engram-E2VID: Reference-Based Event-to-Video Reconstruction via Generative Activation of Appearance Engrams
• BendTwin: Robust Dense-to-Sparse Physical Reconstruction with Bending-Aware Differentiable Spring-Mass Models
• RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos
• Mapping at First Sense: A Lightweight Neural Network-Based Indoor Structures Prediction Method for Robot Autonomous Exploration
• IPV-Bench: Benchmarking Image Protection Methods under Diverse Image-to-Video Generation Scenarios
• Local-Order Auxiliary Losses Can Improve Autoencoder Reconstruction
• EDGS: Eliminating Densification for Efficient Convergence of 3DGS
• TerraMind: Large-Scale Generative Multimodality for Earth Observation
• Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting
• PATFinger: Prompt-Adapted Transferable Fingerprinting against Unauthorized Multimodal Dataset Usage
• Big Brother is Watching: Proactive Deepfake Detection via Learnable Hidden Face
• WaterFlow: Learning Fast & Robust Watermarks using Stable Diffusion
• Efficient and Robust Remote Sensing Image Denoising Using Randomized Approximation of Geodesics' Gramian on the Manifold Underlying the Patch Space
• Rainy: Unlocking Satellite Calibration for Deep Learning in Precipitation
• H-MoRe: Learning Human-centric Motion Representation for Action Analysis
• PG-DPIR: An efficient plug-and-play method for high-count Poisson-Gaussian inverse problems
• Noise2Ghost: Self-supervised deep convolutional reconstruction for ghost imaging
• A Theory of Universal Rate-Distortion-Classification Representations for Lossy Compression
• EBAD-Gaussian: Event-driven Bundle Adjusted Deblur Gaussian Splatting
• Dual-grid parameter choice method with application to image deblurring
• LL-Gaussian: Low-Light Scene Reconstruction and Enhancement via Gaussian Splatting for Novel View Synthesis
• Investigating the Role of Bilateral Symmetry for Inpainting Brain MRI
• CleanMAP: Distilling Multimodal LLMs for Confidence-Driven Crowdsourced HD Map Updates
• DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering
• SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model
• Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images
• TextSplat: Text-Guided Semantic Fusion for Generalizable Gaussian Splatting
• MedIL: Implicit Latent Spaces for Generating Heterogeneous Medical Images at Arbitrary Resolutions
• Universal Rate-Distortion-Classification Representations for Lossy Compression
• Towards Explainable Partial-AIGC Image Quality Assessment
• Data-Importance-Aware Power Allocation for Adaptive Semantic Communication in Computer Vision Applications
• SARFormer -- An Acquisition Parameter Aware Vision Transformer for Synthetic Aperture Radar Data
• MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft
• Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset
• RouterKT: Mixture-of-Experts for Knowledge Tracing
• A Knowledge-guided Adversarial Defense for Resisting Malicious Visual Manipulation
• SN-LiDAR: Semantic Neural Fields for Novel Space-time View LiDAR Synthesis
• Geometric Consistency Refinement for Single Image Novel View Synthesis via Test-Time Adaptation of Diffusion Models
• Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model
• V2V3D: View-to-View Denoised 3D Reconstruction for Light-Field Microscopy
• Conformalized Generative Bayesian Imaging: An Uncertainty Quantification Framework for Computational Imaging
• RASMD: RGB And SWIR Multispectral Driving Dataset for Robust Perception in Adverse Conditions
• Routing to the Right Expertise: A Trustworthy Judge for Instruction-based Image Editing
• Gen3DEval: Using vLLMs for Automatic Evaluation of Generated 3D Objects
• Evaluating the robustness of explainable AI in medical image recognition under natural and adversarial data corruption
• Image registration of 2D optical thin sections in a 3D porous medium: Application to a Berea sandstone digital rock image
• SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering
• Distilling Textual Priors from LLM to Efficient Image Fusion
• AstroClearNet: Deep image prior for multi-frame astronomical image restoration
• GIGA: Generalizable Sparse Image-driven Gaussian Humans
• CamC2V: Context-aware Controllable Video Generation
• Micro-splatting: Multistage Isotropy-informed Covariance Regularization Optimization for High-Fidelity 3D Gaussian Splatting
• Time-Aware Auto White Balance in Mobile Photography
• Meta-Continual Learning of Neural Fields
• HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representation
• AI-Driven Reconstruction of Large-Scale Structure from Combined Photometric and Spectroscopic Surveys
• Flash Sculptor: Modular 3D Worlds from Objects
• Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling
• PartStickers: Generating Parts of Objects for Rapid Prototyping
• DA2Diff: Exploring Degradation-aware Adaptive Diffusion Priors for All-in-One Weather Restoration
• TropoDeep: a deep learning-based model for InSAR tropospheric correction on large-scale interferograms using GNSS and WRF outputs
• Feature Importance-Aware Deep Joint Source-Channel Coding for Computationally Efficient and Adjustable Image Transmission
• Exploring Kernel Transformations for Implicit Neural Representations