Research map / 3D vision / Human pose estimation
Decoupling Human and Camera Motion From Videos in the Wild
Vickie Ye, Georgios Pavlakos, Jitendra Malik, Angjoo Kanazawa
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 |
|---|---|---|---|
| Use scene pixel motion to estimate camera motion and jointly optimize camera scale and human trajectories with a learned motion prior | SLAHMR · EgoBody validation | W-MPJPE: 387.8 -> 141.1 | Improved |
| Use scene pixel motion to estimate camera motion and jointly optimize camera scale and human trajectories with a learned motion prior | SLAHMR · EgoBody validation | WA-MPJPE: 204.9 -> 101.2 | Improved |
| Use scene pixel motion to estimate camera motion and jointly optimize camera scale and human trajectories with a learned motion prior | SLAHMR · EgoBody validation | Acc Err: 307.6 -> 25.78 | Improved |
| Use recovered camera scale α for tracking | PHALP+ · PoseTrack | ID switches: 450 -> 420; -6.7% | Improved |
| Add unscaled [cite] camera estimates | PHALP+ tracking · PoseTrack | ID switches: 450 -> 446; -0.8% | No clear effect |
| Add the final optimization stage with motion prior and camera scale (ablation) | SLAHMR · EgoBody validation | W-MPJPE: 234.0 -> 141.1 | Improved |
| Add the final optimization stage with motion prior and camera scale (ablation) | SLAHMR · EgoBody validation | WA-MPJPE: 152.9 -> 101.2 | Improved |
| Add the final optimization stage with motion prior and camera scale (ablation) | SLAHMR · EgoBody validation | Acc Error: 275.9 -> 25.78 | Improved |
| Optimize world trajectories using estimated camera motion (ablation) | SLAHMR · EgoBody validation | W-MPJPE: 253.6 -> 141.1 | Improved |
| Optimize world trajectories using estimated camera motion (ablation) | SLAHMR · EgoBody validation | WA-MPJPE: 150.3 -> 101.2 | Improved |
| Optimize world trajectories using estimated camera motion (ablation) | SLAHMR · EgoBody validation | Acc Error: 302.1 -> 25.78 | Improved |
| Use estimated cameras and world optimization instead of camera-frame-only PHALP+ (ablation) | PHALP+ · EgoBody validation | W-MPJPE: 387.8 -> 141.1 | 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.
- VIBE — VIBE: Video Inference for Human Body Pose and Shape Estimation (CVPR 2020) · better on 4 of 4 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
- TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos (ECCV 2024 · similarity 0.92)
- HumanMM: Global Human Motion Recovery from Multi-shot Videos (CVPR 2025 · similarity 0.91)
- Reconstructing People, Places, and Cameras (CVPR 2025 · similarity 0.91)
- 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 0.89)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular 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.
