Research map / 3D vision / Depth and stereo
Multi-View 3D Human Tracking in Crowded Scenes
Xiaobai Liu
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 iterative cluster MCMC refinement over the initial 3D tracking (mvKL) (ablation) | multi-view tracker · Dataset-1 | recall: 72.5 % -> 81.4% | Improved |
| add iterative cluster MCMC refinement over the initial 3D tracking (mvKL) (ablation) | multi-view tracker · Dataset-1 | false alarms per frame: 0.8 -> 0.3 | Improved |
| add iterative cluster MCMC refinement over the initial 3D tracking (mvKL) (ablation) | multi-view tracker · EPFL | recall: 80.2% -> 84.7% | Improved |
| add iterative cluster MCMC refinement over the initial 3D tracking (mvKL) (ablation) | multi-view tracker · EPFL | ID switches: 25 -> 16 | Improved |
| add iterative cluster MCMC refinement over the initial 3D tracking (mvKL) (ablation) | multi-view tracker · Dataset-1 parking lot | 3D localization error (m): 0.83 -> 0.61 | Improved |
| add iterative cluster MCMC refinement over the initial 3D tracking (mvKL) (ablation) | multi-view tracker · Dataset-1 office | 3D localization error (m): 0.64 -> 0.33 | Improved |
| use binary-spatial-constraint 3D localization instead of bottom-center footprint homography | 3D localization · Dataset-1 parking lot | 3D localization error (m): 1.21 -> 0.61 | Improved |
Closest papers by meaning
- Multi-View 3D Point Tracking (ICCV 2025 · similarity 0.89)
- Cross-View Tracking for Multi-Human 3D Pose Estimation at Over 100 FPS (CVPR 2020 · similarity 0.89)
- Tracking People with 3D Representations (NeurIPS 2021 · similarity 0.87)
- TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels (NeurIPS 2025 · similarity 0.87)
- Tracking People by Predicting 3D Appearance, Location and Pose (CVPR 2022 · similarity 0.87)
- CoMotion: Concurrent Multi-person 3D Motion (ICLR 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.
