4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
2023/10/12 by Guanjun Wu, Taoran Yi, Wu, Guanjun +15 · 352 citations
Computer Science · #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques #Human Pose and Action Recognition
paper · pdf · doi:10.48550/arxiv.2310.08528
Abstract
Representing and rendering dynamic scenes has been an important but challenging task. Especially, to accurately model complex motions, high efficiency is usually hard to guarantee. To achieve real-time dynamic scene rendering while also enjoying high training and storage efficiency, we propose 4D Gaussian Splatting (4D-GS) as a holistic representation for dynamic scenes rather than applying 3D-GS for each individual frame. In 4D-GS, a novel explicit representation containing both 3D Gaussians and 4D neural voxels is proposed. A decomposed neural voxel encoding algorithm inspired by HexPlane is proposed to efficiently build Gaussian features from 4D neural voxels and then a lightweight MLP is applied to predict Gaussian deformations at novel timestamps. Our 4D-GS method achieves real-time rendering under high resolutions, 82 FPS at an 800×800 resolution on an RTX 3090 GPU while maintaining comparable or better quality than previous state-of-the-art methods. More demos and code are available at https://guanjunwu.github.io/4dgs/.
Cited by
- Next Best View Selections for Semantic and Dynamic 3D Gaussian Splatting
- GenSplatCodec: Feed-Forward Gaussian Splatting Compression via One-Step Diffusion
- Learning Dynamic Scene Reconstruction with Sinusoidal Geometric Priors
- Parameter-Efficient Adaptation of SAM3 for Prompt-Driven Surgical Concept Segmentation
- 3D Gaussian Splatting for Scientific Particle Data Compression and Rendering
- TOM-GS: Editable Video Representation via Temporal Opacity Modulation of Static 3D Gaussians
- URHead: A Unified UV-Space Representation for Joint Mesh-3DGS Optimization in Head Avatars
- Ground4D: Consistency-Aware 4D Reconstruction from Monocular Video
- SketchPlay: Intuitive Creation of Physically Realistic VR Content with Gesture-Driven Sketching
- AirGS: Real-Time 4D Gaussian Streaming for Free-Viewpoint Video Experiences
- SirenPose: Dynamic Scene Reconstruction via Geometric Supervision
- 4D Gaussian Splatting as a Learned Dynamical System
- Geometric-Photometric Event-based 3D Gaussian Ray Tracing
- G3Splat: Geometrically Consistent Generalizable Gaussian Splatting
- LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents
- Instant Expressive Gaussian Head Avatars at Over 100 FPS
- M-PhyGs: Multi-Material Object Dynamics from Video
- GeoPredict: Leveraging Predictive Kinematics and 3D Gaussian Geometry for Precise VLA Manipulation
- Broadening View Synthesis of Dynamic Scenes from Constrained Monocular Videos
- HGS: Hybrid Gaussian Splatting with Static-Dynamic Decomposition for Compact Dynamic View Synthesis
- Consistent Instance Field for Dynamic Scene Understanding
- GaussianPlant: Structure-aligned Gaussian Splatting for 3D Reconstruction of Plants
- ASAP-Textured Gaussians: Enhancing Textured Gaussians with Adaptive Sampling and Anisotropic Parameterization
- LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction
- Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All
- Animus3D: Text-driven 3D Animation via Motion Score Distillation
- MultiEgo: A Multi-View Egocentric Video Dataset for 4D Scene Reconstruction
- VDAWorld: World Modelling via VLM-Directed Abstraction and Simulation
- GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting
- TraceFlow: Dynamic 3D Reconstruction of Specular Scenes Driven by Ray Tracing
- D2GSLAM: 4D Dynamic Gaussian Splatting SLAM
- StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation
- LoGoColor: Local-Global 3D Colorization for 360° Scenes
- MoRel: Long-Range Flicker-Free 4D Motion Modeling via Anchor Relay-based Bidirectional Blending with Hierarchical Densification
- Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform
- Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objects
- SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting
- WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling
- Multi-view Pyramid Transformer: Look Coarser to See Broader
- EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopy
- Tracking-Guided 4D Generation: Foundation-Tracker Motion Priors for 3D Model Animation
- TED-4DGS: Temporally Activated and Embedding-based Deformation for 4DGS Compression
- Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting
- BulletTime: Decoupled Control of Time and Camera Pose for Video Generation
- Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation
- Splat-SAP: Feed-Forward Gaussian Splatting for Human-Centered Scene with Scale-Aware Point Map Reconstruction
- UTrice: Unifying Primitives in Differentiable Ray Tracing and Rasterization via Triangles for Particle-Based 3D Scenes
- SyncTrack4D: Cross-Video Motion Alignment and Video Synchronization for Multi-Video 4D Gaussian Splatting
- SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation
- A Fast Volumetric Capture and Reconstruction Pipeline for Dynamic Point Clouds and Gaussian Splats
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding
- Flux4D: Flow-based Unsupervised 4D Reconstruction
- SurfFill: Completion of LiDAR Point Clouds via Gaussian Surfel Splatting
- PoreTrack3D: A Benchmark for Dynamic 3D Gaussian Splatting in Pore-Scale Facial Trajectory Tracking
- EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Fly
- Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer
- Cross-Temporal 3D Gaussian Splatting for Sparse-View Guided Scene Update
- Geometry-Consistent 4D Gaussian Splatting for Sparse-Input Dynamic View Synthesis
- DenoiseGS: Gaussian Reconstruction Model for Burst Denoising
- Gaussians on Fire: High-Frequency Reconstruction of Flames
- RemedyGS: Defend 3D Gaussian Splatting against Computation Cost Attacks
- Endo-G2T: Geometry-Guided & Temporally Aware Time-Embedded 4DGS For Endoscopic Scenes
- IDSplat: Instance-Decomposed 3D Gaussian Splatting for Driving Scenes
- MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes
- Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstruction
- Any4D: Open-Prompt 4D Generation from Natural Language and Images
- ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes
- Alias-free 4D Gaussian Splatting
- RoboArmGS: High-Quality Robotic Arm Splatting via Bézier Curve Refinement
- CUS-GS: A Compact Unified Structured Gaussian Splatting Framework for Multimodal Scene Representation
- REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting
- PhysMorph-GS: Differentiable Shape Morphing via Joint Optimization of Physics and Rendering Objectives
- Vorion: A RISC-V GPU with Hardware-Accelerated 3D Gaussian Rendering and Training
- ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimation
- Complex-Valued 2D Gaussian Representation for Computer-Generated Holography
- Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction
- CPSL: Representing Volumetric Video via Content-Promoted Scene Layers
- Gaussian Splatting-based Low-Rank Tensor Representation for Multi-Dimensional Image Recovery
- Changes in Real Time: Online Scene Change Detection with Multi-View Fusion
- Dynamic Avatar-Scene Rendering from Human-centric Context
- AHA! Animating Human Avatars in Diverse Scenes with Gaussian Splatting
- NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from Videos
- 4DSTR: Advancing Generative 4D Gaussians with Spatial-Temporal Rectification for High-Quality and Consistent 4D Generation
- Sparse4DGS: 4D Gaussian Splatting for Sparse-Frame Dynamic Scene Reconstruction
- ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction with Fewer Primitives
- Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material Field
- StreamSTGS: Streaming Spatial and Temporal Gaussian Grids for Real-Time Free-Viewpoint Video
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
- Splatography: Sparse multi-view dynamic Gaussian Splatting for filmmaking challenges
- DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos
- 4D Neural Voxel Splatting: Dynamic Scene Rendering with Voxelized Guassian Splatting
- Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models
- SAGS: Self-Adaptive Alias-Free Gaussian Splatting for Dynamic Surgical Endoscopic Reconstruction
- Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture
- DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting
- SEE4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting
- HEIR: Learning Graph-Based Motion Hierarchies
- The Impact and Outlook of 3D Gaussian Splatting
- 3DGBGS: 3D Granular Ball Gaussian Splatting for Compact Novel View Synthesis
- Diff2DGS: Reliable Reconstruction of Occluded Surgical Scenes via 2D Gaussian Splatting
- Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving
- SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time
- Demeter: A Parametric Model of Crop Plant Morphology from the Real World
- EA3D: Online Open-World 3D Object Extraction from Streaming Videos
- Proactive Scene Decomposition and Reconstruction
- VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting
- EndoWave: Rational-Wavelet 4D Gaussian Splatting for Endoscopic Reconstruction
- PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis
- Inverse Image-Based Rendering for Light Field Generation from Single Images
- From Far and Near: Perceptual Evaluation of Crowd Representations Across Levels of Detail
- Advances in 4D Representation: Geometry, Motion, and Interaction
- MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting
- Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos
- From Volume Rendering to 3D Gaussian Splatting: Theory and Applications
- DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion
- Iterative Motion Compensation for Canonical 3D Reconstruction from UAV Plant Images Captured in Windy Conditions
- Leveraging Learned Image Prior for 3D Gaussian Compression
- Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Rendering
- Trace Anything: Representing Any Video in 4D via Trajectory Fields
- FlashWorld: High-quality 3D Scene Generation within Seconds
- Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction
- Vectorized Video Representation with Easy Editing via Hierarchical Spatio-Temporally Consistent Proxy Embedding
- Ev4DGS: Novel-view Rendering of Non-Rigid Objects from Monocular Event Streams
- MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference
- Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos
- 4DGS-Craft: Consistent and Interactive 4D Gaussian Splatting Editing
- Color3D: Controllable and Consistent 3D Colorization with Personalized Colorizer
- P-4DGS: Predictive 4D Gaussian Splatting with 90× Compression
- Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild
- Visibility-Aware Densification for 3D Gaussian Splatting in Dynamic Urban Scenes
- LTGS: Long-Term Gaussian Scene Chronology From Sparse View Updates
- DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream
- SCas4D: Structural Cascaded Optimization for Boosting Persistent 4D Novel View Synthesis
- MorphoSim: An Interactive, Controllable, and Editable Language-guided 4D World Simulator
- Optimized Minimal 4D Gaussian Splatting
- From Tokens to Nodes: Semantic-Guided Motion Control for Dynamic 3D Gaussian Splatting
- Instant4D: 4D Gaussian Splatting in Minutes
- Universal Beta Splatting
- Parameterizing Dataset Distillation via Gaussian Splatting
- HBSplat: Robust Sparse-View Gaussian Reconstruction with Hybrid-Loss Guided Depth and Bidirectional Warping
- ReCon-GS: Continuum-Preserved Gaussian Streaming for Fast and Compact Reconstruction of Dynamic Scenes
- Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos
- UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation
- Uni4D-LLM: A Unified SpatioTemporal-Aware VLM for 4D Understanding and Generation
- OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting
- Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos
- Dynamic Novel View Synthesis in High Dynamic Range
- 4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans
- TSOG: A Format For Temporally And Spatially Ordered Gaussians
- Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints
- VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Video
- 4D-MoDe: Towards Editable and Scalable Volumetric Streaming via Motion-Decoupled 4D Gaussian Compression
- 4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
- ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos
- Neural-MMGS: Multi-modal Neural Gaussian Splats for Large-Scale Scene Reconstruction
- MoAngelo: Motion-Aware Neural Surface Reconstruction for Dynamic Scenes
- MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting
- RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes
- FMGS-Avatar: Mesh-Guided 2D Gaussian Splatting with Foundation Model Priors for 3D Monocular Avatar Reconstruction
- 4DRadar-GS: Self-Supervised Dynamic Driving Scene Reconstruction with 4D Radar
- Beyond Averages: Open-Vocabulary 3D Scene Understanding with Gaussian Splatting and Bag of Embeddings
- M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments
- Every Camera Effect, Every Time, All at Once: 4D Gaussian Ray Tracing for Physics-based Camera Effect Data Generation
- T2Bs: Text-to-Character Blendshapes via Video Generation
- A Survey of Deep Learning-based Point Cloud Denoising
- MOGS: Monocular Object-guided Gaussian Splatting in Large Scenes
- FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
- ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction
- Advances and Trends in the 3D Reconstruction of the Shape and Motion of Animals
- Towards Integrating Multi-Spectral Imaging with Gaussian Splatting
- UPGS: Unified Pose-aware Gaussian Splatting for Dynamic Scene Deblurring
- Scale-GS: Efficient Scalable Gaussian Splatting via Redundancy-filtering Training on Streaming Content
- DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes
- MAPo : Motion-Aware Partitioning of Deformable 3D Gaussian Splatting for High-Fidelity Dynamic Scene Reconstruction
- Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion
- Style4D-Bench: A Benchmark Suite for 4D Stylization
- ColorGS: High-fidelity Surgical Scene Reconstruction with Colored Gaussian Splatting
- Deep Sensorimotor Control by Imitating Predictive Models of Human Motion
- DriveSplat: Decoupled Driving Scene Reconstruction with Geometry-enhanced Partitioned Neural Gaussians
- 2D Gaussians Meet Visual Tokenizer
- InnerGS: Internal Scenes Reconstruction and Segmentation via Factorized 3D Gaussian Splatting
- 4DNeX: Feed-Forward 4D Generative Modeling Made Easy
- Improving Densification in 3D Gaussian Splatting for High-Fidelity Rendering
- Versatile Video Representation via Feed-Forward 2D Gaussian Splatting Tokenization
- Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS
- A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation
- TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videos
- GaussianUpdate: Continual 3D Gaussian Splatting Update for Changing Environments
- ReferSplat: Referring Segmentation in 3D Gaussian Splatting
- SAGOnline: Segment Any Gaussians Online
- NeeCo: Image Synthesis of Novel Instrument States Based on Dynamic and Deformable 3D Gaussian Reconstruction
- Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D Generation
- Fading the Digital Ink: A Universal Black-Box Attack Framework for 3DGS Watermarking Systems
- CharacterShot: Controllable and Consistent 4D Character Animation
- 3D Gaussian Representations with Motion Trajectory Field for Dynamic Scene Reconstruction
- Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video
- Laplacian Analysis Meets Dynamics Modelling: Gaussian Splatting for 4D Reconstruction
- Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions
- SplitGaussian: Reconstructing Dynamic Scenes via Visual Geometry Decomposition
- Low-Frequency First: Eliminating Floating Artifacts in 3D Gaussian Splatting
- GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstruction
- PMGS: Reconstruction of Projectile Motion Across Large Spatiotemporal Spans via 3D Gaussian Splatting
- VDEGaussian: Video Diffusion Enhanced 4D Gaussian Splatting for Dynamic Urban Scenes Modeling
- MASIV: Toward Material-Agnostic System Identification from Videos
- Multimodal Referring Segmentation: A Survey
- PointGauss: Point Cloud-Guided Multi-Object Segmentation for Gaussian Splatting
- Cooperative Perception: A Resource-Efficient Framework for Multi-Drone 3D Scene Reconstruction Using Federated Diffusion and NeRF
- Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis
- MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion
- Enhanced Velocity Field Modeling for Gaussian Video Reconstruction
- Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models
- Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction
- Reconstructing 4D Spatial Intelligence: A Survey
- Automated 3D-GS Registration and Fusion via Skeleton Alignment and Gaussian-Adaptive Features
- SonicGauss: Position-Aware Physical Sound Synthesis for 3D Gaussian Representations
- DASH: 4D Hash Encoding with Self-Supervised Decomposition for Real-Time Dynamic Scene Rendering
- 3DGauCIM: Accelerating Static/Dynamic 3D Gaussian Splatting via Digital CIM for High Frame Rate Real-Time Edge Rendering
- Learning Efficient and Generalizable Human Representation with Human Gaussian Model
- MVG4D: Image Matrix-Based Multi-View and Motion Generation for 4D Content Creation from a Single Image
- High-fidelity 3D Gaussian Inpainting: preserving multi-view consistency and photorealistic details
- Temporal Smoothness-Aware Rate-Distortion Optimized 4D Gaussian Splatting
- Gaussian kernel-based motion measurement
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos
- VolSegGS: Segmentation and Tracking in Dynamic Volumetric Scenes via Deformable 3D Gaussians
- iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos
- MMOne: Representing Multiple Modalities in One Scene
- MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second
- M2DAO-Talker: Harmonizing Multi-granular Motion Decoupling and Alternating Optimization for Talking-head Generation
- Spline Deformation Field
- EscherNet++: Simultaneous Amodal Completion and Scalable View Synthesis through Masked Fine-Tuning and Enhanced Feed-Forward 3D Reconstruction
- SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction
- MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation
- Spatial-Temporal Aware Visuomotor Diffusion Policy Learning
- LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
- ClipGS: Clippable Gaussian Splatting for Interactive Cinematic Visualization of Volumetric Medical Data
- FillGS: Filling Observation Gaps in 4D Gaussian Splatting via Viewpoint-Time Selection and Generative Refinement
- D-FCGS: Feedforward Compression of Dynamic Gaussian Splatting for Free-Viewpoint Videos
- 4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture
- ArmGS: Composite Gaussian Appearance Refinement for Modeling Dynamic Urban Environments
- Neural Dynamic Modes: Computational Imaging of Dynamical Systems from Sparse Observations
- LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling
- HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars
- LOD-GS: Level-of-Detail-Sensitive 3D Gaussian Splatting for Detail Conserved Anti-Aliasing
- OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving
- Dynamic View Synthesis as an Inverse Problem
- Endo-4DGX: Robust Endoscopic Scene Reconstruction and Illumination Correction with Gaussian Splatting
- STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene
- SpeeDe3DGS: Speedy Deformable 3D Gaussian Splatting with Temporal Pruning and Motion Grouping
- FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity
- RoboPearls: Editable Video Simulation for Robot Manipulation
- HuSc3D: Human Sculpture dataset for 3D object reconstruction
- PhotonSplat: 3D Scene Reconstruction and Colorization from SPAD Sensors
- MADrive: Memory-Augmented Driving Scene Modeling
- CoCo4D: Comprehensive and Complex 4D Scene Generation
- HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis
- AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models
- 4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time
- ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs
- BulletGen: Improving 4D Reconstruction with Bullet-Time Generation
- 4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos
- Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation
- 3D Gaussian Splatting for Fine-Detailed Surface Reconstruction in Large-Scale Scene
- Part2GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting
- Vision in Action: Learning Active Perception from Human Demonstrations
- Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry
- TextureSplat: Per-Primitive Texture Mapping for Reflective Gaussian Splatting
- Hybrid Mesh-Gaussian Representation for Efficient Indoor Scene Reconstruction
- Rasterizing Wireless Radiance Field via Deformable 2D Gaussian Splatting
- Efficient multi-view training for 3D Gaussian Splatting
- Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors
- Metropolis-Hastings Sampling for 3D Gaussian Reconstruction
- Gaussian Mapping for Evolving Scenes
- Anti-Aliased 2D Gaussian Splatting
- DynaSplat: Dynamic-Static Gaussian Splatting with Hierarchical Motion Decomposition for Scene Reconstruction
- HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene
- Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision
- Reconstructing Heterogeneous Biomolecules via Hierarchical Gaussian Mixtures and Part Discovery
- Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation
- FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction
- ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting
- UAV4D: Dynamic Neural Rendering of Human-Centric UAV Imagery using Gaussian Splatting
- Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience
- FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting
- DyTact: Capturing Dynamic Contacts in Hand-Object Manipulation
- PhysGaia: A Physics-Aware Benchmark with Multi-Body Interactions for Dynamic Novel View Synthesis
- GSCodec Studio: A Modular Framework for Gaussian Splat Compression
- DeepVerse: 4D Autoregressive Video Generation as a World Model
- PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation
- ViVo: A Dataset for Volumetric Video Reconstruction and Compression
- Tackling View-Dependent Semantics in 3D Language Gaussian Splatting
- Hi-Dyna Graph: Hierarchical Dynamic Scene Graph for Robotic Autonomy in Human-Centric Environments
- Mobi-π: Mobilizing Your Robot Learning Policy
- Quality assessment of 3D human animation: Subjective and objective evaluation
- CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
- STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering
- Diffusion-Denoised Hyperspectral Gaussian Splatting
- Wideband RF Radiance Field Modeling Using Frequency-embedded 3D Gaussian Splatting
- ParticleGS: Learning Neural Gaussian Particle Dynamics from Videos for Prior-free Physical Motion Extrapolation
- Weather-Magician: Reconstruction and Rendering Framework for 4D Weather Synthesis In Real Time
- CAD-SLAM: Consistency-Aware Dynamic SLAM with Dynamic-Static Decoupled Mapping
- Geometry-guided Online 3D Video Synthesis with Multi-View Temporal Consistency
- D2-4DGS: Dual-Depth Guided Sparse-Camera 4D Gaussian Splatting
- CTRL-GS: Cascaded Temporal Residue Learning for 4D Gaussian Splatting
- Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance
- UniqueSplat: View-Conditioned 3D Gaussian Splatting for Generalizable 3D Reconstruction
- SPAR: Self-supervised Placement-Aware Representation Learning for Distributed Sensing
- Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction
- SHaDe: Compact and Consistent Dynamic 3D Reconstruction via Tri-Plane Deformation and Latent Diffusion
- DeGS: A Scalable 3DGS Architecture via Decoupled Workload Parsing and Reorganization
- ASTRA: Asynchronous Spatio-Temporal Reconstruction via Trajectory Alignment
- MGStream: Motion-aware 3D Gaussian for Streamable Dynamic Scene Reconstruction
- Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation
- LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding
- MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos
- Advances in Radiance Field for Dynamic Scene: From Neural Field to Gaussian Field
- HyperGS: Fast and Generalizable Gaussian Video Representation
- DLO-Splatting: Tracking Deformable Linear Objects Using 3D Gaussian Splatting
- ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction
- GIFStream: 4D Gaussian-based Immersive Video with Feature Stream
- AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting
- Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields
- SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splatting
- AdvSplat: Adversarial Attacks on Feed-Forward Gaussian Splatting Models
- Quo Vadis, World Modeling?
- ShowMak3r: Compositional TV Show Reconstruction
- 4DGS-CC: A Contextual Coding Framework for 4D Gaussian Splatting Data Compression
- Fast Voxelization and Level of Detail for Microgeometry Rendering
- STP4D: Spatio-Temporal-Prompt Consistent Modeling for Text-to-4D Gaussian Splatting
- When Gaussian Meets Surfel: Ultra-fast High-fidelity Radiance Field Rendering
- ACA-GS: Adaptive-Capacity Anchored Gaussian Splatting for Compact Dynamic Radiance Fields
- UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models
- Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning
- SmallGS: Gaussian Splatting-based Camera Pose Estimation for Small-Baseline Videos
- MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video
- EG-Gaussian: Epipolar Geometry and Graph Network Enhanced 3D Gaussian Splatting
- St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World
- CompGS++: Compressed Gaussian Splatting for Static and Dynamic Scene Representation
- GSAC: Leveraging Gaussian Splatting for Photorealistic Avatar Creation with Unity Integration
- Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization
- Digital Twin Generation from Visual Data: A Survey
- BEV-GS: Feed-forward Gaussian Splatting in Bird's-Eye-View for Road Reconstruction
- BendTwin: Robust Dense-to-Sparse Physical Reconstruction with Bending-Aware Differentiable Spring-Mass Models
- Media Meets Communication in 6G: Fundamentals, Key Technologies, and Applications
- EDGS: Eliminating Densification for Efficient Convergence of 3DGS
- Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting
- In-2-4D: Inbetweening from Two Single-View Images to 4D Generation
- Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
- Better artificial intelligence does not mean better models of biology
- HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representation
- Let it Snow! Animating 3D Gaussian Scenes with Dynamic Weather Effects via Physics-Guided Score Distillation
- 3D Gaussian Splatting as a New Era: A Survey
- Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images
Related