Research map / 3D vision / Human pose estimation
OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery
Yiwen Zhao, Ce Zheng, Yufu Wang, Hsueh-Han Daniel Yang, Liting Wen, László A. Jeni
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 velocity regularization loss (ablation) | OnlineHMR · 3DPW | Accel: 8.9 -> 6.4 | Improved |
| add velocity regularization loss (ablation) | OnlineHMR · EMDB-1 | Jitter: 70.1 -> 33.7 | Improved |
| apply soft human mask instead of hard mask in SLAM input (ablation) | DROID-SLAM · Camera trajectory ATE | ATE: 1.55 -> 1.07 | Improved |
| apply soft human mask instead of hard mask in SLAM input (ablation) | MASt3R-SLAM · Camera trajectory ATE | ATE: 0.96 -> 0.83 | Improved |
| mask human region in SLAM input (hard mask vs none) (ablation) | DROID-SLAM · Camera trajectory ATE | ATE: 2.52 -> 1.55 | Improved |
| use online causal method instead of offline chunk-based (OnlineHMR vs TRAM) | OnlineHMR · EMDB-2 (world coords) | WA-MPJPE100: 76.4 -> 93.5 | Hurt |
| OnlineHMR vs prior online Human3R in camera coords | OnlineHMR · 3DPW | PA-MPJPE: 44.1 -> 43.7 | Improved |
| OnlineHMR vs prior online Human3R in world coords | OnlineHMR · EMDB-2 (world coords) | WA-MPJPE100: 112.2 -> 93.5 | Improved |
| OnlineHMR vs Human3R speed | OnlineHMR · EMDB-2 (world coords) | FPS: 4.8 -> 3.3 | Hurt |
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.
- Human3R — Human3R: Everyone Everywhere All at Once (ICLR 2026) · better on 4 of 7 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
- Synergistic Global-space Camera and Human Reconstruction from Videos (CVPR 2024 · similarity 0.89)
- GenHMR: Generative Human Mesh Recovery (AAAI 2025 · similarity 0.89)
- WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion (CVPR 2024 · similarity 0.89)
- ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization (ICML 2025 · similarity 0.89)
- FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery (NeurIPS 2026 · similarity 0.88)
- HumanMM: Global Human Motion Recovery from Multi-shot Videos (CVPR 2025 · similarity 0.88)
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.
