Research map / 3D vision / Human pose estimation
Single-Stage Is Enough: Multi-Person Absolute 3D Pose Estimation
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 |
|---|---|---|---|
| add PDQM to the decoupled regression model (ablation) | DRM · MuPoTS-3D | PCKabs: 32.1 -> 35.5 | Helped |
| add PDQM to the decoupled regression model (ablation) | DRM · MuPoTS-3D | PCKroot: 32.3 -> 40.8 | Helped |
| add PDQM to the decoupled regression model (ablation) | DRM · MuPoTS-3D | PCKrel: 81.3 -> 81.4 | No clear effect |
| add DAPL to the decoupled regression model (ablation) | DRM · MuPoTS-3D | PCKabs: 32.1 -> 39.8 | Helped |
| add DAPL to the decoupled regression model (ablation) | DRM · MuPoTS-3D | PCKroot: 32.3 -> 44.1 | Helped |
| add DAPL to the decoupled regression model (ablation) | DRM · MuPoTS-3D | PCKrel: 81.3 -> 83.7 | Helped |
| use the 2D center point rather than the root point as the 2D pose regression clue (ablation) | DRM · COCO | AP: 63.9 -> 67.2 | Helped |
| use the root point rather than the 2D center point as the depth regression clue (ablation) | DRM · MuPoTS-3D | absolute depth deviation | Helped |
| use single-stage DRM instead of SMAP | multi-person absolute 3D pose estimation · MuPoTS-3D matched people | PCKrel: 80.5 -> 85.1 | Helped |
| use single-stage DRM instead of SMAP | multi-person absolute 3D pose estimation · MuPoTS-3D matched people | PCKabs: 38.7 -> 41.0 | Helped |
| use single-stage DRM instead of SMAP | multi-person absolute 3D pose estimation · Panoptic mean | RtError: 85.5 -> 60.9 | Helped |
Closest papers by meaning
- Multi-View Multi-Person 3D Pose Estimation With Plane Sweep Stereo (CVPR 2021 · similarity 0.88)
- Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks (CVPR 2021 · similarity 0.87)
- PoseIRM: Enhance 3D Human Pose Estimation on Unseen Camera Settings via Invariant Risk Minimization (CVPR 2024 · similarity 0.86)
- Relative Pose Estimation through Affine Corrections of Monocular Depth Priors (CVPR 2025 · similarity 0.85)
- MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation (CVPR 2025 · similarity 0.85)
- TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation (CVPR 2024 · similarity 0.85)
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.