Research map / 3D vision / Human pose estimation
Contact-guided Real2Sim from Monocular Video with Planar Scene Primitives
Zihan Wang, Jiashun Wang, Jeff Tan, Yiwen Zhao, Jessica K. Hodgins, Shubham Tulsiani, Deva Ramanan
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 |
|---|---|---|---|
| replace dense NKSR mesh with planar primitives (ablation) | CRISP · overall humanoid RL | success rate (%): 79.3% -> 93.1% | Improved |
| replace TSDF mesh with planar primitives (ablation) | CRISP · overall humanoid RL | success rate (%): 75.9% -> 93.1% | Improved |
| replace dense meshes with planar primitives (ablation) | CRISP · simulation throughput | FPS: 16K -> 23K | Improved |
| use NKSR instead of planar primitives (ablation) | CRISP · PROX bidirectional Chamfer | Chamfer distance: 0.187 -> 0.163 | Improved |
| use planar primitives instead of NKSR (ablation) | CRISP · PROX one-way Chamfer | Chamfer distance: 0.187 -> 0.174 | Improved |
| use TSDF instead of planar primitives (ablation) | CRISP · PROX | non-penetration: 0.947 -> 0.925 | Hurt |
| add contact-guided scene completion (ablation) | CRISP · PROX | bidirectional Chamfer distance: 0.193 -> 0.187 | Improved |
| add contact-guided scene completion (ablation) | CRISP · PROX | success rate (%): 90.9% -> 90.9% | No clear effect |
| add RL motion refinement (ablation) | CRISP · EMDB HMR | WA-MPJPE100 (mm): 78.16 -> 70.60 | Improved |
| add RL motion refinement (ablation) | CRISP · EMDB HMR | jitter: 13.04 -> 8.14 | Improved |
| add RL motion refinement (ablation) | VideoMimic · EMDB HMR | WA-MPJPE100 (mm): 110.64 -> 145.24 | Hurt |
| CRISP versus VideoMimic | CRISP · humanoid RL overall | success rate (%): 44.8% -> 93.1% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TRAM — TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos (ECCV 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.90)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.89)
- Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos (NeurIPS 2026 · similarity 0.88)
- Synergistic Global-space Camera and Human Reconstruction from Videos (CVPR 2024 · similarity 0.87)
- InteractVLM: 3D Interaction Reasoning from 2D Foundational Models (CVPR 2025 · similarity 0.87)
- Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image (NeurIPS 2026 · 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.
