Research map / 3D vision / 3D generation
Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models
Hongyu Li, Wanjia Fu, Xiaoyan Cong, Zekun Li, Binghao Huang, Hanxiao Jiang, Xintong He, Yiqing Liang, Rao Fu, Tao Lu, Srinath Sridhar, Kevin Smith and 2 more
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 tactile signals to tracking optimization (ablation) | Deform360 markerless tracking · Deform360 warped point cloud | Chamfer distance: 1.41 × 10^{-4} -> 2.71 × 10^{-5} m^2 | Improved |
| physics-based PhysTwin vs learning-based particle models | 3D world models · Deform360 per-episode | Chamfer distance: future CD 0.073 (PGND) / 0.044 (ParticleFormer) -> 0.014 (PhysTwin) | Improved |
| use post-trained Cosmos video model instead of ParticleFormer | world model · Deform360 multi-episode reconstruction | PSNR: 26.263 -> 27.748 | Improved |
| use Cosmos video model instead of ParticleFormer | world model · Deform360 multi-episode future prediction | PSNR: 25.203 -> 24.950 | Hurt |
| use Cosmos video model instead of ParticleFormer | world model · Deform360 multi-object zero-shot | PSNR: 23.312 -> 25.042 | Improved |
| ParticleFormer instead of PGND | learning-based 3D world model · Deform360 multi-object zero-shot | Chamfer distance: 0.429 -> 0.038 | Improved |
Closest papers by meaning
- DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos (NeurIPS 2026 · similarity 0.92)
- DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning (NeurIPS 2026 · similarity 0.87)
- DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling (NeurIPS 2025 · similarity 0.87)
- Lifting Motion to the 3D World via 2D Diffusion (CVPR 2025 · similarity 0.87)
- LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE (NeurIPS 2026 · similarity 0.87)
- RoboScape: Physics-informed Embodied World Model (NeurIPS 2025 · similarity 0.87)
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.
