Research map / 3D vision / Human pose estimation
Occluded Human Mesh Recovery
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 |
|---|---|---|---|
| apply top-down OCHMR rather than ROMP | human mesh recovery · 3DPW-PC | MPJPE: 119.7 -> 112.2 | Helped |
| apply top-down OCHMR rather than ROMP | human mesh recovery · OCHuman | AP: 15.6 -> 37.7 | Helped |
| apply top-down OCHMR rather than ROMP | human mesh recovery · CrowdPose | AP: 18.9 -> 23.6 | Helped |
| apply OCHMR rather than PARE | human mesh recovery under object occlusion · 3DPW-OCC | MPJPE: 90.5 -> 93.5 | Hurt |
| apply OCHMR rather than PARE | human mesh recovery under object occlusion · 3DOH | MPJPE: 63.3 -> 98.6 | Hurt |
| add CoNorm context injection instead of early feature concatenation (ablation) | OCHMR · OCHuman | AP: 30.6 -> 37.7 | Helped |
| add multi-person losses rather than use only L_single (ablation) | OCHMR · OCHuman | AP: 32.8 -> 37.7 | Helped |
| add CAR loss (ablation) | OCHMR · OCHuman | AP: 36.9 vs 37.7 | No clear effect |
| use I2LMeshNet as the top-down base method | OCHMR · 3DPW-PC | MPJPE: 123.6 -> 110.0 | Helped |
| use PyMaf as the top-down base method | OCHMR · OCHuman | AP: 19.3 -> 39.1 | Helped |
Closest papers by meaning
- DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery (CVPR 2024 · similarity 0.90)
- FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery (NeurIPS 2026 · similarity 0.88)
- Instance-aware Contrastive Learning for Occluded Human Mesh Reconstruction (CVPR 2024 · similarity 0.87)
- ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization (ICML 2025 · similarity 0.87)
- Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery (NeurIPS 2024 · similarity 0.86)
- SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens (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.