mlsanityData to 7 Oct 2026

Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians

arXiv 2403.09434 ↗First posted 14 Mar 2024cs.CVcited by 92

Not on the map. Why?

Abstract (arXiv)

Reconstructing and simulating elastic objects from visual observations is crucial for applications in computer vision and robotics. Existing methods, such as 3D Gaussians, model 3D appearance and geometry, but lack the ability to estimate physical properties for objects and simulate them. The core challenge lies in integrating an expressive yet efficient physical dynamics model. We propose Spring-Gaus, a 3D physical object representation for reconstructing and simulating elastic objects from videos of the object from multiple viewpoints. In particular, we develop and integrate a 3D Spring-Mass model into 3D Gaussian kernels, enabling the reconstruction of the visual appearance, shape, and physical dynamics of the object. Our approach enables future prediction and simulation under various initial states and environmental properties. We evaluate Spring-Gaus on both synthetic and real-world datasets, demonstrating accurate reconstruction and simulation of elastic objects. Project page: https://zlicheng.com/spring_gaus/.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). Builds on 43 of its 52 references that are in the map. First posted on arXiv 14 Mar 2024.

Builds on

43 of 52 references.

References · 43

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2023Segment Anythingcited by 8,158
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  6. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  7. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  8. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  9. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  10. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  11. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  12. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
31 more
  1. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  2. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  3. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  4. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
  5. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  6. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  7. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
  8. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  9. 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 470
  10. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 470
  11. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 368
  12. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 339
  13. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  14. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  15. 2018Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluidscited by 219
  16. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 210
  17. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  18. 2023PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identificationcited by 145
  19. 2023DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splattingcited by 124
  20. 20213D Neural Scene Representations for Visuomotor Controlcited by 110
  21. 2022Learning Multi-Object Dynamics with Compositional Neural Radiance Fieldscited by 63
  22. 2021DiffPD: Differentiable Projective Dynamicscited by 62
  23. 2023Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamicscited by 56
  24. 2022Physics Informed Neural Fields for Smoke Reconstruction with Sparse Datacited by 52
  25. 2022Differentiable Physics Simulation of Dynamics-Augmented Neural Objectscited by 45
  26. 2023Flow supervision for Deformable NeRFcited by 42
  27. 2022NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fieldscited by 36
  28. 2022Implicit Neural Spatial Representations for Time-dependent PDEscited by 35
  29. 2023Inferring Hybrid Neural Fluid Fields from Videoscited by 18
  30. 2023Learning Vortex Dynamics for Fluid Inference and Predictioncited by 17
  31. 2023Fluid Simulation on Neural Flow Mapscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 12; 2025: 42; 2026: 38.

92 papers.

Sort:

By area:

  1. 2024Recent Advances in 3D Gaussian Splattingcited by 130
  2. 2025CAST: Component-Aligned 3D Scene Reconstruction from an RGB Imagecited by 101
  3. 2025PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videoscited by 78
  4. 2025Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signalscited by 51
  5. 2024RoboGSim: A Real2Sim2Real Robotic Gaussian Splatting Simulatorcited by 50
  6. 2024GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulationcited by 48
  7. 2024PhysMotion: Physics-Grounded Dynamics From a Single Imagecited by 45
  8. 2025WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actionscited by 43
  9. 2025PhysX-3D: Physical-Grounded 3D Asset Generationcited by 40
  10. 2025PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generationcited by 39
  11. 2024Physically Compatible 3D Object Modeling from a Single Imagecited by 38
  12. 2024Neural Material Adaptor for Visual Grounding of Intrinsic Dynamicscited by 30
38 more
  1. 2024Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splattingcited by 30
  2. 2025Real-to-Sim Robot Policy Evaluation with Gaussian Splatting Simulation of Soft-Body Interactionscited by 27
  3. 2025Generative Physical AI in Vision: A Surveycited by 24
  4. 2024Phys4DGen: Physics-Compliant 4D Generation with Multi-Material Composition Perceptioncited by 23
  5. 2025Particle-Grid Neural Dynamics for Learning Deformable Object Models from RGB-D Videoscited by 22
  6. 2025Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixelscited by 22
  7. 2024Neural Fields in Robotics: A Surveycited by 21
  8. 2025FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Videocited by 21
  9. 2026LLM-as-a-Verifier: A General-Purpose Verification Frameworkcited by 21
  10. 2024GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMscited by 20
  11. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  12. 2025Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulationcited by 18
  13. 2025FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocitycited by 13
  14. 2025Grounding Creativity in Physics: A Brief Survey of Physical Priors in AIGCcited by 11
  15. 2025TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videoscited by 11
  16. 2025PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesiscited by 9
  17. 2024MaGS: Reconstructing and Simulating Dynamic 3D Objects with Mesh-adsorbed Gaussian Splattingcited by 8
  18. 2025Learning 3D-Gaussian Simulators from RGB Videoscited by 8
  19. 2025MASIV: Toward Material-Agnostic System Identification from Videoscited by 7
  20. 2025Seeing the Wind from a Falling Leafcited by 7
  21. 2025TwinAligner: Visual-Dynamic Alignment Empowers Physics-aware Real2Sim2Real for Robotic Manipulationcited by 7
  22. 2026PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangementcited by 7
  23. 2025Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material Fieldcited by 6
  24. 2026MOSIV: Multi-Object System Identification from Videoscited by 6
  25. 2025ParticleGS: Learning Neural Gaussian Particle Dynamics from Videos for Prior-free Physical Motion Extrapolationcited by 5
  26. 2025PMGS: Reconstruction of Projectile Motion Across Large Spatiotemporal Spans via 3D Gaussian Splattingcited by 5
  27. 2026ReconPhys: Reconstruct Appearance and Physical Attributes from Single Videocited by 5
  28. 2026PhyCo: Learning Controllable Physical Priors for Generative Motioncited by 5
  29. 2024GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objectscited by 4
  30. 2025PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animationcited by 4
  31. 2025ProJo4D: Progressive Joint Optimization for Sparse-View Inverse Physics Estimationcited by 4
  32. 2025From 2D to 3D Cognition: A Brief Survey of General World Modelscited by 4
  33. 2025Advances in 4D Representation: Geometry, Motion, and Interactioncited by 4
  34. 2025Gaussian-Augmented Physics Simulation and System Identification with Complex Colliderscited by 4
  35. 2025NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from Videoscited by 4
  36. 2026SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulationcited by 4
  37. 2025PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided LLMcited by 3
  38. 2025VisionLaw: Inferring Interpretable Intrinsic Dynamics from Visual Observations via Bilevel Optimizationcited by 3

50 most cited of 92 All 92 (JSON)