Research map / 3D vision / Human pose estimation
Body Meshes as Points
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 |
|---|---|---|---|
| use a single-stage spatial-depth point representation for localization and mesh recovery | BMP · Panoptic | MPJPE: 143.2 -> 135.4 | Helped |
| use a single-stage spatial-depth point representation for localization and mesh recovery | BMP · MuPoTS-3D | 3DPCK (All): 69.12 -> 73.83 | Helped |
| use a single-stage spatial-depth point representation for localization and mesh recovery | BMP · 3DPW | PCK: 25.8 -> 32.1; 33.9 | Mixed |
| replace the 2D spatial representation with the spatial-depth representation and FPN depth levels (ablation) | BMP · Panoptic | MPJPE: 145.6 -> 135.4 | Helped |
| replace the 2D spatial representation with the spatial-depth representation and FPN depth levels (ablation) | BMP · 3DPW | MPJPE: 110.8 -> 104.1 | Helped |
| replace the 2D spatial representation with the spatial-depth representation and FPN depth levels (ablation) | BMP · MuPoTS-3D | 3DPCK: 69.34 -> 73.83 | Helped |
| add full pair-wise ordinal depth loss (ablation) | BMP · MuPoTS-3D | Relative depth ordering accuracy: 91.42% -> 94.50% | Helped |
| add keypoint-aware occlusion augmentation (ablation) | BMP · Panoptic | MPJPE: 148.9 -> 135.4 | Helped |
| add keypoint-aware occlusion augmentation (ablation) | BMP · 3DPW | MPJPE: 125.9 -> 104.1 | Helped |
| add keypoint-aware occlusion augmentation (ablation) | BMP · MuPoTS-3D | 3DPCK: 71.71 -> 73.83 | Helped |
| replace keypoint-aware occlusion augmentation with random synthetic occlusion (ablation) | BMP · MuPoTS-3D | 3DPCK: 71.71 -> 70.78 | Hurt |
Closest papers by meaning
- BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation (CVPR 2025 · similarity 0.87)
- SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens (CVPR 2025 · similarity 0.87)
- MeshPose: Unifying DensePose and 3D Body Mesh Reconstruction (CVPR 2024 · similarity 0.86)
- AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation (CVPR 2024 · similarity 0.86)
- Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation (NeurIPS 2024 · similarity 0.86)
- Reconstructing People, Places, and Cameras (CVPR 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.