Research map / 3D vision / Human pose estimation
Learning Human Mesh Recovery in 3D Scenes
Zehong Shen, Zhi Cen, Sida Peng, Qing Shuai, Hujun Bao, Xiaowei Zhou
Read the paperCheck 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 |
|---|---|---|---|
| predict scene-aware root position and mesh in a single forward pass | METRO · RICH | G-MPJPE: 511.7 -> 264.6 | Improved |
| predict scene-aware root position and mesh in a single forward pass | METRO · PROX | G-MPJPE: 265.6 -> 150.4 | Improved |
| replace scene-aware optimization with a learned single-pass method | METRO + SA-Opt · RICH | G-MPJPE: 563.1 -> 264.6 | Improved |
| add scene-aware root and contact estimation (ablation) | SA-HMR root module · RICH | RtErr: 510.8 -> 284.7 | Improved |
| add scene-aware root and contact estimation (ablation) | SA-HMR root module · PROX | RtErr: 364.2 -> 132.3 | Improved |
| add scene-aware mesh recovery after root refinement (ablation) | SA-HMR · RICH | RtErr: 284.7 -> 246.5 | Improved |
| add scene-aware mesh recovery after root refinement (ablation) | SA-HMR · PROX | RtErr: 132.3 -> 111.8 | Improved |
| use a parallel cross-attention scene network instead of early feature fusion (ablation) | SA-HMR · RICH | G-MPJPE: 304.8 -> 264.6 | Improved |
| use a parallel cross-attention scene network instead of early feature fusion (ablation) | SA-HMR · RICH | CErr: 10.2 -> 8.9 | Improved |
| replace estimated root with ground-truth root (ablation) | SA-HMR mesh recovery · RICH | MPJPE: 93.9 -> 89.2 | Improved |
| replace estimated contacts with ground-truth contacts (ablation) | SA-HMR mesh recovery · RICH | MPJPE: 93.9 -> 90.4 | Improved |
| replace estimated root and contacts with ground truth (ablation) | SA-HMR mesh recovery · RICH | MPJPE: 93.9 -> 76.7 | Improved |
Closest papers by meaning
- Recovering 3D Human Mesh From Monocular Images: A Survey (TPAMI 2023 · similarity 0.90)
- FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery (NeurIPS 2026 · similarity 0.89)
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.89)
- BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation (CVPR 2025 · similarity 0.88)
- DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery (CVPR 2024 · similarity 0.88)
- GenHMR: Generative Human Mesh Recovery (AAAI 2025 · 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.
