Research map / 3D vision / Gaussian splatting
GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects
Yidi Shao, Mu Huang, Chen Change Loy, Bo Dai
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add mass conservation constraint (ablation) | GausSim · Mothorchids Seen | l2 error: 2.19 -> 1.78 | Improved |
| add mass conservation constraint (ablation) | GausSim · Mothorchids Unseen 83 | l2 error: 1.90 -> 1.85 | Improved |
| add momentum conservation loss (ablation) | GausSim · Mothorchids Seen | l2 error: 2.64 -> 1.78 | Improved |
| add momentum conservation loss (ablation) | GausSim · Mothorchids Unseen 83 | l2 error: 1.91 -> 1.85 | Improved |
| train jointly on all domains instead of per object (ablation) | GausSim · Mothorchids Seen | l2 error: 1.78 -> 1.90 | No clear effect |
| train jointly on all domains instead of per object (ablation) | GausSim · Mothorchids Unseen 83 | l2 error: 1.85 -> 1.88 | No clear effect |
| add hierarchical structure (ablation) | GausSim · Mothorchids efficiency | forward time (s): 0.36 -> 0.13 | Improved |
| add hierarchical structure (ablation) | GausSim · Mothorchids efficiency | GPU memory (GB): 3.5 -> 2.1 | Improved |
| add hierarchical structure (ablation) | GausSim · Mothorchids | predictions ratio N_F/N_K: 0.05 | Improved |
| use GausSim instead of PhysDreamer | GausSim · Carnation Unseen 83 | l2 error: 6.15 -> 6.02 | Improved |
| use GausSim instead of DG4D | GausSim · Carnation Unseen 83 | l2 error: 31.63 -> 6.02 | Improved |
Closest papers by meaning
- PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics (CVPR 2024 · similarity 0.88)
- OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation (ICLR 2025 · similarity 0.87)
- NeuMA: Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics (NeurIPS 2024 · similarity 0.84)
- GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulation (NeurIPS 2024 · similarity 0.84)
- UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation (CVPR 2025 · similarity 0.84)
- Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Rendering (CVPR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
