Research map / 3D vision / Human pose estimation
Direct Multi-view Multi-person 3D Pose Estimation
Read the paperCheck 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 |
|---|---|---|---|
| use direct multi-view pose regression rather than VoxelPose's pipeline | MvP · Panoptic | AP25: 84.0 -> 92.3 | Helped |
| use direct multi-view pose regression rather than VoxelPose's pipeline | MvP · Panoptic | inference time (ms): 320 -> 170 | Helped |
| add RayConv camera-ray geometry encoding (ablation) | MvP · Panoptic | AP25: 87.5 -> 92.3 | Helped |
| add RayConv camera-ray geometry encoding (ablation) | MvP · Panoptic | MPJPE: 17.4 -> 15.8 | Helped |
| use hierarchical person-and-joint queries instead of independent per-joint queries (ablation) | MvP · Panoptic | AP25: 67.4 -> 82.5 | Helped |
| use hierarchical person-and-joint queries instead of independent per-joint queries (ablation) | MvP · Panoptic | MPJPE: 41.2 -> 19.5 | Helped |
| add input-dependent query adaptation to hierarchical queries (ablation) | MvP · Panoptic | AP25: 82.5 -> 92.3 | Helped |
| add input-dependent query adaptation to hierarchical queries (ablation) | MvP · Panoptic | MPJPE: 19.5 -> 15.8 | Helped |
| raise confidence threshold from 0.0 to 0.4 (ablation) | MvP · Panoptic | AP25: 93.1 -> 89.2 | Hurt |
| raise confidence threshold from 0.0 to 0.4 (ablation) | MvP · Panoptic | MPJPE: 16.3 -> 15.0 | Helped |
| increase decoder layers from 2 to 6 (ablation) | MvP · Panoptic | AP25: 6.3 -> 92.3 | Helped |
| increase decoder layers from 2 to 6 (ablation) | MvP · Panoptic | MPJPE: 49.6 -> 15.8 | Helped |
Closest papers by meaning
- End-to-End Multi-Person Pose Estimation With Transformers (CVPR 2022 · similarity 0.91)
- End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer (AAAI 2026 · similarity 0.90)
- SVTformer: Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation (AAAI 2025 · similarity 0.89)
- MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation (CVPR 2025 · similarity 0.89)
- SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation (CVPR 2024 · similarity 0.89)
- Multiple View Geometry Transformers for 3D Human Pose Estimation (CVPR 2024 · similarity 0.88)
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.