Research map / 3D vision / Human pose estimation
Multi-View Multi-Person 3D Pose Estimation With Plane Sweep Stereo
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Replace explicit cross-view matching with plane-sweep pose-aware depth regression | Multi-view multi-person 3D pose estimation · Campus | PCP average (%): 96.7 to 97.0 | Helped |
| Replace explicit cross-view matching with plane-sweep pose-aware depth regression | Multi-view multi-person 3D pose estimation · Shelf | PCP average (%): 97.4 to 97.9 | Helped |
| Use plane-sweep pose-aware depth regression instead of VoxelPose | CMU Panoptic · CMU Panoptic | MPJPE: 17.68mm -> 16.75mm | Helped |
| Use local soft-argmax rather than standard soft-argmax (ablation) | Person-level depth regression · Campus | PCP average (%): 96.3 -> 97.0 | Helped |
| Use local soft-argmax rather than standard soft-argmax (ablation) | Person-level depth regression · Shelf | PCP average (%): 97.6 -> 97.9 | Helped |
| Reduce person-level depth planes from 64 to 16 (ablation) | Plane-sweep depth regression · Shelf | PCP (%): 97.9 -> 97.5 | Hurt |
| Reduce joint-level depth planes from 64 to 16 (ablation) | Plane-sweep depth regression · Shelf | PCP (%): 97.9 -> 97.2 | Hurt |
| Reduce camera count from 5 to 4 (ablation) | Plane-sweep depth regression · Shelf | PCP (%): 97.9 -> 97.5 | Hurt |
| Reduce camera count from 5 to 3 (ablation) | Plane-sweep depth regression · Shelf | PCP (%): 97.9 -> 95.1 | Hurt |
| Reduce camera count from 5 to 2 (ablation) | Plane-sweep depth regression · Shelf | PCP (%): 97.9 -> 92.5 | Hurt |
| Train with randomly sampled camera viewpoints and evaluate on the dataset camera set (ablation) | Plane-sweep depth regression · Shelf | PCP (%): 97.9 -> 97.7 | No clear effect |
| Use plane-sweep pose-aware depth regression instead of VoxelPose | Multi-view 3D pose estimation · Campus | inference speed (fps): 5.5 -> 110.0 | Helped |
Closest papers by meaning
- Fast and Robust Multi-Person 3D Pose Estimation From Multiple Views (CVPR 2019 · similarity 0.91)
- Cross-View Tracking for Multi-Human 3D Pose Estimation at Over 100 FPS (CVPR 2020 · similarity 0.90)
- Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes - The Importance of Multiple Scene Constraints (CVPR 2018 · similarity 0.89)
- Direct Multi-view Multi-person 3D Pose Estimation (NeurIPS 2021 · similarity 0.89)
- Single-Stage Is Enough: Multi-Person Absolute 3D Pose Estimation (CVPR 2022 · similarity 0.88)
- 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.