RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

2020/01/01 by Zachary Teed, Jia Deng · 185 citations
Computer Science · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Image Enhancement Techniques

paper · doi:10.1007/978-3-030-58536-5_24

crossref issued 2020/01/01 · crossref published 2020/01/01 · crossref published-print 2020/01/01 · openalex publication_date 2020/01/01 · crossref created 2020/11/02 · crossref published-online 2020/11/03 · crossref deposited 2024/11/03 · openalex created_date 2025/10/10 · crossref indexed 2026/07/30 · openalex updated_date 2026/07/31

Cited by

• Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles
• Diff2DGS: Reliable Reconstruction of Occluded Surgical Scenes via 2D Gaussian Splatting
• Scene-Centric Unsupervised Video Panoptic Segmentation
• Robust Consistent Video Depth Estimation
• Guidance and Teaching Network for Video Salient Object Detection
• LIFE: Lighting Invariant Flow Estimation
• See the Speaker: Crafting High-Resolution Talking Faces from Speech with Prior Guidance and Region Refinement
• VC4VG: Optimizing Video Captions for Text-to-Video Generation
• Neural Trajectory Fields for Dynamic Novel View Synthesis
• EndoWave: Rational-Wavelet 4D Gaussian Splatting for Endoscopic Reconstruction
• VALA: Learning Latent Anchors for Training-Free and Temporally Consistent
• FAME: Fairness-aware Attention-modulated Video Editing
• Efficient Large-Deformation Medical Image Registration via Recurrent Dynamic Correlation
• 3DPR: Single Image 3D Portrait Relight using Generative Priors
• Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding
• Learning Optical Flow from a Few Matches
• Generative Point Tracking with Flow Matching
• Video-As-Prompt: Unified Semantic Control for Video Generation
• Advances in 4D Representation: Geometry, Motion, and Interaction
• Video Consistency Distance: Enhancing Temporal Consistency for Image-to-Video Generation via Reward-Based Fine-Tuning
• Is This Tracker On? A Benchmark Protocol for Dynamic Tracking
• Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos
• GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimation
• VelocityNet: Real-Time Crowd Anomaly Detection via Person-Specific Velocity Analysis
• AV1 Motion Vector Fidelity and Application for Efficient Optical Flow
• Iterative Motion Compensation for Canonical 3D Reconstruction from UAV Plant Images Captured in Windy Conditions
• C4D: 4D Made from 3D through Dual Correspondences
• 3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation
• Multi-modal video data-pipelines for machine learning with minimal human supervision
• MatchAttention: Matching the Relative Positions for High-Resolution Cross-View Matching
• Edit-Your-Interest: Efficient Video Editing via Feature Most-Similar Propagation
• Removing Cost Volumes from Optical Flow Estimators
• Active Tactile Exploration for Rigid Body Pose and Shape Estimation
• What If : Understanding Motion Through Sparse Interactions
• Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction
• FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
• Vectorized Video Representation with Easy Editing via Hierarchical Spatio-Temporally Consistent Proxy Embedding
• CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion
• Point Prompting: Counterfactual Tracking with Video Diffusion Models
• Implicit Feature Pyramid Network for Object Detection
• Injecting Frame-Event Complementary Fusion into Diffusion for Optical Flow in Challenging Scenes
• Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learning
• FreeViS: Training-free Video Stylization with Inconsistent References
• Mono4DEditor: Text-Driven 4D Scene Editing from Monocular Video via Point-Level Localization of Language-Embedded Gaussians
• FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
• ReSplat: Learning Recurrent Gaussian Splats
• Hybrid Neural Fusion for Full-frame Video Stabilization
• Trajectory Conditioned Cross-embodiment Skill Transfer
• Progressive and Selective Fusion Network for High Dynamic Range Imaging
• VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning
• PickStyle: Video-to-Video Style Transfer with Context-Style Adapters
• DynamicEval: Rethinking Evaluation for Dynamic Text-to-Video Synthesis
• MATRIX: Mask Track Alignment for Interaction-aware Video Generation
• Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
• TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation
• Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion Model
• Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics
• Character Mixing for Video Generation
• Pack and Force Your Memory: Long-form and Consistent Video Generation
• Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation
• Learning Efficient Meshflow and Optical Flow from Event Cameras
• Feedback Matters: Augmenting Autonomous Dissection with Visual and Topological Feedback
• MorphoSim: An Interactive, Controllable, and Editable Language-guided 4D World Simulator
• Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch
• Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
• An Efficient Quality Metric for Video Frame Interpolation Based on Motion-Field Divergence
• IMAGEdit: Let Any Subject Transform
• Continuous Space-Time Video Super-Resolution with 3D Fourier Fields
• High Resolution and High-Speed Live Optical Flow Velocimetry
• Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
• Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint
• Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution
• Dual-view Snapshot Compressive Imaging via Optical Flow Aided Recurrent Neural Network
• Pixel Motion Diffusion is What We Need for Robot Control
• Temporal-Aware Iterative Speech Model for Dementia Detection
• UniTransfer: Video Concept Transfer via Progressive Spatial and Timestep Decomposition
• Is Space-Time Attention All You Need for Video Understanding?
• VIMD: Monocular Visual-Inertial Motion and Depth Estimation
• TESO: Online Tracking of Essential Matrix by Stochastic Optimization
• UniCam: Taming Unified Diffusion Models in Noise Space for Camera-controllable Video Rendering
• FADE: A Task-Agnostic Upsampling Operator for Encoder–Decoder Architectures
• Threshold Domain Sizes for Multifractality in Sea Ice Deformation
• CoWTracker: Tracking by Warping instead of Correlation
• Topology Aware Neural Interpolation of Scalar Fields
• AutoFlow: Learning a Better Training Set for Optical Flow
• Surgical Video Understanding with Label Interpolation
• VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models
• ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment
• LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation
• ConfidentSplat: Confidence-Weighted Depth Fusion for Accurate 3D Gaussian Splatting SLAM
• OS-DiffVSR: Towards One-step Latent Diffusion Model for High-detailed Real-world Video Super-Resolution
• Neural Atlas Graphs for Dynamic Scene Decomposition and Editing
• Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Model
• WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance
• RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes
• RaFD: Flow-Guided Radar Detection for Robust Autonomous Driving
• BEV-ODOM2: Enhanced BEV-based Monocular Visual Odometry with PV-BEV Fusion and Dense Flow Supervision for Ground Robots
• Teacher-Guided Pseudo Supervision and Cross-Modal Alignment for Audio-Visual Video Parsing
• UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place Solution
• StereoCarla: A High-Fidelity Driving Dataset for Generalizable Stereo
• 4DRadar-GS: Self-Supervised Dynamic Driving Scene Reconstruction with 4D Radar
• VROOM - Visual Reconstruction over Onboard Multiview
• OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
• FractalPINN-Flow: A Fractal-Inspired Network for Unsupervised Optical Flow Estimation with Total Variation Regularization
• DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras
• Phantom-Insight: Adaptive Multi-cue Fusion for Video Camouflaged Object Detection with Multimodal LLM
• UniVerse-1: Unified Audio-Video Generation via Stitching of Experts
• Motion Aware ViT-based Framework for Monocular 6-DoF Spacecraft Pose Estimation
• FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
• Generation of realistic cardiac ultrasound sequences with ground truth motion and speckle decorrelation
• SSGaussian: Semantic-Aware and Structure-Preserving 3D Style Transfer
• Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Control
• TEn-CATG:Text-Enriched Audio-Visual Video Parsing with Multi-Scale Category-Aware Temporal Graph
• Weakly-Supervised Learning of Dense Functional Correspondences
• Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery
• ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association
• DAOVI: Distortion-Aware Omnidirectional Video Inpainting
• UTA-Sign: Unsupervised Thermal Video Augmentation via Event-Assisted Traffic Signage Sketching
• Adam SLAM - the last mile of camera calibration with 3DGS
• UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning
• AutoQ-VIS: Improving Unsupervised Video Instance Segmentation via Automatic Quality Assessment
• Q-Align: Alleviating Attention Leakage in Zero-Shot Appearance Transfer via Query-Query Alignment
• Style4D-Bench: A Benchmark Suite for 4D Stylization
• Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization
• DOVE: Learning Deformable 3D Objects by Watching Videos
• SMTrack: End-to-End Trained Spiking Neural Networks for Multi-Object Tracking in RGB Videos
• 6-DoF Object Tracking with Event-based Optical Flow and Frames
• Online 3D Gaussian Splatting Modeling with Novel View Selection
• Self-Supervised Sparse Sensor Fusion for Long Range Perception
• PersonaVlog: Personalized Multimodal Vlog Generation with Multi-Agent Collaboration and Iterative Self-Correction
• AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes
• Precise Action-to-Video Generation Through Visual Action Prompts
• Unifying Scale-Aware Depth Prediction and Perceptual Priors for Monocular Endoscope Pose Estimation and Tissue Reconstruction
• FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation
• STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
• Cooperative Face Liveness Detection from Optical Flow
• AEGIS: Authenticity Evaluation Benchmark for AI-Generated Video Sequences
• HM-Talker: Hybrid Motion Modeling for High-Fidelity Talking Head Synthesis
• EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba
• Trajectory-aware Shifted State Space Models for Online Video Super-Resolution
• Surg-InvNeRF: Invertible NeRF for 3D tracking and reconstruction in surgical vision
• TOTNet: Occlusion-Aware Temporal Tracking for Robust Ball Detection in Sports Videos
• HKT: A Biologically Inspired Framework for Modular Hereditary Knowledge Transfer in Neural Networks
• Fact-Checking at Scale: Multimodal AI for Authenticity and Context Verification in Online Media
• Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videos
• SelfHVD: Self-Supervised Handheld Video Deblurring
• Learning an Implicit Physics Model for Image-based Fluid Simulation
• Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition
• S²VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix
• The Escalator Problem: Identifying Implicit Motion Blindness in AI for Accessibility
• Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation
• Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction
• Consistent and Controllable Image Animation with Motion Linear Diffusion Transformers
• CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping
• Confidence-guided Adaptive Gate and Dual Differential Enhancement for Video Salient Object Detection
• Efficient Bayer-Domain Video Computer Vision with Fast Motion Estimation and Learned Perception Residual
• ETA: Energy-based Test-time Adaptation for Depth Completion
• TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferring
• TSMS-SAM2: Multi-scale Temporal Sampling Augmentation and Memory-Splitting Pruning for Promptable Video Object Segmentation and Tracking in Surgical Scenarios
• Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens
• BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment
• Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline
• CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event Localization
• Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm
• PMGS: Reconstruction of Projectile Motion Across Large Spatiotemporal Spans via 3D Gaussian Splatting
• DELTAv2: Accelerating Dense 3D Tracking
• D3: Training-Free AI-Generated Video Detection Using Second-Order Features
• Occlusion-robust Stylization for Drawing-based 3D Animation
• Video Forgery Detection with Optical Flow Residuals and Spatial-Temporal Consistency
• Enhanced Velocity Field Modeling for Gaussian Video Reconstruction
• MamV2XCalib: V2X-based Target-less Infrastructure Camera Calibration with State Space Model
• Training-free Geometric Image Editing on Diffusion Models
• Learning to Prune Branches in Modern Tree-Fruit Orchards
• Exploiting Aliasing for Manga Restoration
• DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments
• Unleashing the Power of Motion and Depth: A Selective Fusion Strategy for RGB-D Video Salient Object Detection
• JWB-DH-V1: Benchmark for Joint Whole-Body Talking Avatar and Speech Generation Version 1
• HumanSAM: Classifying Human-centric Forgery Videos in Human Spatial, Appearance, and Motion Anomaly
• CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation
• ForCenNet: Foreground-Centric Network for Document Image Rectification
• DepthFlow: Exploiting Depth-Flow Structural Correlations for Unsupervised Video Object Segmentation
• TransFlow: Motion Knowledge Transfer from Video Diffusion Models to Video Salient Object Detection
• Leveraging Sparse LiDAR for RAFT-Stereo: A Depth Pre-Fill Perspective
• Event-Based De-Snowing for Autonomous Driving