Research map / 3D vision / Human pose estimation
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
Zitian Wang, Xuecheng Nie, Xiaochao Qu, Yunpeng Chen, Si Liu
Check 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 root joint rather than bounding-box center (ablation) | DAS · CMU Panoptic | MPJPE: 65.3 -> 62.5 | Improved |
| Add recursive update (ablation) | DAS with root center · CMU Panoptic | MPJPE: 62.5 -> 57.6 | Improved |
| Add MLE for the learned joint-location distribution (ablation) | DAS with root center · CMU Panoptic | MPJPE: 62.5 -> 58.8 | Improved |
| Combine recursive update with MLE (ablation) | DAS with root center · CMU Panoptic | MPJPE: 62.5 -> 56.3 | Improved |
| Use a larger backbone (ablation) | DAS with recursive update and MLE · CMU Panoptic | MPJPE: 56.3 -> 54.4 | Improved |
| Add recursive update (ablation) | DAS · CMU Panoptic | MPJPE: 62.5 -> 58.6 | Improved |
| Add multi-source update (ablation) | DAS with one recursive update layer · CMU Panoptic | MPJPE: 58.6 -> 58.2 | Improved |
| Increase recursive update depth from one to two layers (ablation) | DAS with multi-source update · CMU Panoptic | MPJPE: 58.2 -> 57.9 | Improved |
| Increase recursive update depth from two to three layers (ablation) | DAS with multi-source update · CMU Panoptic | MPJPE: 57.9 -> 57.6 | Improved |
| Use single-stage DAS instead of two-stage top-down methods | Multi-person 3D pose estimation · MuPoTS-3D | PCK_rel: 82.7 vs 83.7* | Mixed |
| Use single-stage DAS instead of bottom-up methods | Multi-person 3D pose estimation · MuPoTS-3D | PCK_rel: 82.7 vs 73.5 | Improved |
| Use single-stage DAS instead of the strongest listed CMU Panoptic baseline | Multi-person 3D pose estimation · CMU Panoptic | MPJPE: 55.1* -> 53.8 | Improved |
Closest papers by meaning
- Multi-Person Pose Regression With Distribution-Aware Single-Stage Models (TPAMI 2024 · similarity 0.95)
- Single-Stage Multi-Person Pose Machines (ICCV 2019 · similarity 0.89)
- Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose Estimation (ECCV 2020 · similarity 0.89)
- MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation (CVPR 2025 · similarity 0.89)
- Direct Multi-view Multi-person 3D Pose Estimation (NeurIPS 2021 · similarity 0.89)
- SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation (CVPR 2024 · similarity 0.87)
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.
