Research map / Video / Video generation
DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction
Yufu Wang, Evonne Ng, Soyong Shin, Rawal Khirodkar, Yuan Dong, Zhaoen Su, Jinhyung Park, Kris Kitani, Alexander Richard, Fabian Prada, Michael Zollhöfer
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 world-space diffusion model after camera-space model (ablation) | DuoMo · EMDB ablation | W-MPJPE: 180.2 -> 167.1 | Improved |
| add world-space diffusion model after camera-space model (ablation) | DuoMo · EMDB ablation | jitter: 32.6 -> 8.7 | Improved |
| add camera-space stage before world-space model (ablation) | DuoMo · EMDB ablation | W-MPJPE: 445.1 -> 167.1 | Improved |
| add height conditioning | DuoMo camera-space model · EMDB camera-space (24 joints) | MPJPE: 67.1 -> 59.5 | Improved |
| add guided sampling (ablation) | DuoMo · Egobody full segment | RTE: 1.6 -> 1.1 | Improved |
| add guided sampling (ablation) | DuoMo · Egobody occluded segments | W-MPJPE-Occ: 193.1 -> 175.4 | Improved |
| generate sparse mesh instead of SMPLX parameters (ablation) | DuoMo world model · EMDB ablation | W-MPJPE: 182.5 -> 164.8 | Improved |
| add world-space model at low camera noise (ablation) | DuoMo · EMDB camera noise sweep | W-MPJPE | Mixed |
| add world-space model (ablation) | DuoMo · Egobody full segment | W-MPJPE: 174.2 -> 109.3 | Improved |
| add height conditioning | DuoMo world-space · EMDB world-space (24 joints) | W-MPJPE: 171.6 -> 167.1 | No clear effect |
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.
- GENMO — GENMO: A GENeralist Model for Human MOtion (ICCV 2025) · better on 6 of 6 shared results
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
- Reconstructing People, Places, and Cameras (CVPR 2025 · similarity 0.88)
- WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion (CVPR 2024 · similarity 0.88)
- Lifting Motion to the 3D World via 2D Diffusion (CVPR 2025 · similarity 0.88)
- RoHM: Robust Human Motion Reconstruction via Diffusion (CVPR 2024 · similarity 0.88)
- HumanMM: Global Human Motion Recovery from Multi-shot Videos (CVPR 2025 · similarity 0.88)
- Move-in-2D: 2D-Conditioned Human Motion Generation (CVPR 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.
