Research map / 3D vision / Human pose estimation
Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery
Fengyuan Yang, Kerui Gu, Ha Linh Nguyen, Tze Ho Elden Tse, Angela Yao
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 scale calibration (ablation) | OfCaM · EMDB2 | WA-MPJPE: 111.29 vs 335.53 (w/o L2G) | Improved |
| add scale calibration (ablation) | OfCaM · EMDB2 | RTE: 9.61 -> 2.41 | Improved |
| add scale calibration (ablation) | OfCaM · EMDB2 | ATE-S: 6.30 -> 1.33 | Improved |
| add local-to-global adjustment (ablation) | OfCaM · EMDB2 | WA-MPJPE: 111.29 -> 108.24 | Improved |
| add local-to-global adjustment (ablation) | OfCaM · EMDB2 | W-MPJPE: 347.60 -> 317.88 | Improved |
| add local-to-global adjustment (ablation) | OfCaM · EMDB2 (challenging sequences) | W-MPJPE: 520.89 -> 376.17 | Improved |
| add local-to-global adjustment (ablation) | OfCaM · EMDB2 (challenging sequences) | WA-MPJPE: 160.54 -> 142.40 | Improved |
| add scale-calibrated camera motion on top of L2G only (ablation) | OfCaM · EMDB2 | RTE: 7.68 -> 2.21 | Improved |
| use feet instead of head as reference joint (ablation) | OfCaM · EMDB2 | WA-MPJPE: 369.11 -> 108.24 | Improved |
| use feet instead of pelvis as reference joint (ablation) | OfCaM · EMDB2 | WA-MPJPE: 292.44 -> 108.24 | Improved |
| use feet instead of pelvis as reference joint (ablation) | OfCaM · EMDB2 | ATE-S: 5.51 -> 1.25 | Improved |
| OfCaM vs WHAM (w/ DPVO) | OfCaM · EMDB2 | RTE: 6.0 -> 2.2 | Improved |
Closest papers by meaning
- Synergistic Global-space Camera and Human Reconstruction from Videos (CVPR 2024 · similarity 0.90)
- WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion (CVPR 2024 · similarity 0.88)
- Reconstructing People, Places, and Cameras (CVPR 2025 · similarity 0.88)
- HumanMM: Global Human Motion Recovery from Multi-shot Videos (CVPR 2025 · similarity 0.87)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.86)
- FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments (AAAI 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.
