Research map / 3D vision / 3D generation
Physics-Based Interaction with 3D Objects via Video Generation
Tianyuan Zhang, Hong-Xing Yu, Rundi Wu, Brandon Y Feng, Changxi Zheng, Noah Snavely, Jiajun Wu, William T. Freeman
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 |
|---|---|---|---|
| estimate material properties via video-prior distillation (PhysDreamer) instead of manually set values (PhysGaussian) | PhysDreamer · Motion realism user study | 2AFC preference: 80.8% prefer PhysDreamer | Improved |
| simulate physical dynamics with estimated materials instead of distilling a deformation field | PhysDreamer vs DreamGaussian4D · Visual quality / motion realism user study | 2AFC preference: 70.0% visual quality, 63.5% motion realism | Improved |
| PhysDreamer vs real captured videos | PhysDreamer · Motion realism user study | 2AFC preference: 53.7% overall; 86% alocasia, 29% cord, 35% tulip | Mixed |
| PhysDreamer vs real captured videos on visual quality | PhysDreamer · Visual quality user study | 2AFC preference: 37.3% prefer PhysDreamer | Hurt |
| add second-view reference video for self-occluding objects (ablation) | PhysDreamer · Alocasia | 2AFC preference: 81.0% visual quality, 86.0% motion realism prefer two-view | Improved |
| PhysDreamer vs PhysGaussian on hat scene | PhysDreamer · Hat, motion realism | 2AFC preference: 57% (motion), 50% (visual quality) | No clear effect |
Closest papers by meaning
- DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos (NeurIPS 2026 · similarity 0.88)
- PhysX-3D: Physical-Grounded 3D Asset Generation (NeurIPS 2025 · similarity 0.88)
- DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors (AAAI 2025 · similarity 0.88)
- PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation (NeurIPS 2025 · similarity 0.87)
- OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation (ICLR 2025 · similarity 0.87)
- DecoupledGaussian: Object-Scene Decoupling for Physics-Based Interaction (CVPR 2025 · similarity 0.86)
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.
