Research map / 3D vision / Human pose estimation
Shape-Aware Multi-Person Pose Estimation From Multi-View Images
Zijian Dong, Jie Song, Xu Chen, Chen Guo, Otmar Hilliges
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 shape-aware refinement (multi-view constraints plus SMPL regularization) on top of the initial 3D proposals (ablation) | Ours · Association Dataset | F1-score (%): 83.4 -> 89.2 | Improved |
| add shape-aware refinement (ablation) | Ours · Association Dataset | Precision (%): 83.7 -> 90.1 | Improved |
| add shape-aware refinement (ablation) | Ours · Association Dataset | Recall (%): 82.8 -> 89.0 | Improved |
| use the proposed fitting (joint 3D pose optimization with body prior) instead of SMPL-only fitting (ablation) | Ours · Association Dataset | F1-score (%): 77.8 -> 89.2 | Improved |
| use the proposed fitting instead of SMPL-only fitting (ablation) | Ours · Association Dataset | precision (%): 78.3% -> 90.1% | Improved |
| use learned gradient descent for optimization instead of standard optimization (ablation) | Ours · Association Dataset | runtime: 2s -> 0.1s; 100 -> 14 iterations (20x speed-up) | Improved |
| add SMPL body-model regularization for joints with low confidence (ablation) | Ours · Association Dataset (MPJPE, low-confidence joints) | MPJPE | Improved |
| add SMPL body-model regularization for joints with confidence above 0.25 (ablation) | Ours · Association Dataset (MPJPE, high-confidence joints) | MPJPE | No clear effect |
| use the proposed 3D proposal generation instead of VoxelPose (ablation) | proposal generation · Association Dataset (human proposal) | F1-score (%): 72.8 -> 96.4 | Improved |
| use the proposed 3D proposal generation instead of Zhang et al. (ablation) | proposal generation · Association Dataset (human proposal) | Recall (%): 51.2 -> 94.2 | Improved |
| use the proposed method instead of a 3D-supervised learned method (VoxelPose) on unseen data | multi-view pose estimation · Association Dataset | F1-score (%): 60.3 -> 89.2 | Improved |
| use the proposed method instead of 3D-supervised VoxelPose trained on the Shelf set | multi-view pose estimation · Shelf | PCP average (%): 97.0 -> 96.9 | No clear effect |
Closest papers by meaning
- Dual Networks Based 3D Multi-Person Pose Estimation From Monocular Video (TPAMI 2022 · similarity 0.92)
- Fast and Robust Multi-Person 3D Pose Estimation From Multiple Views (CVPR 2019 · similarity 0.92)
- Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes - The Importance of Multiple Scene Constraints (CVPR 2018 · similarity 0.92)
- Probabilistic 3D Human Shape and Pose Estimation From Multiple Unconstrained Images in the Wild (CVPR 2021 · similarity 0.92)
- Direct Multi-view Multi-person 3D Pose Estimation (NeurIPS 2021 · similarity 0.92)
- MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation (CVPR 2025 · similarity 0.90)
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.
