Research map / 3D vision / Human pose estimation
CoEvoer: Collaborative Evolution Transformer for Upper-Body Expressive Human Pose and Shape Estimation
Yuxiang Zhao, Wei Huang, Yujie Song, Liu Wang, Huan Zhao
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 |
|---|---|---|---|
| add explicit bidirectional cross-part attention (Collaborative Evolution Enhancer) instead of self-attention on concatenated part features (ablation) | CoEvoer · UBody (all) | MPVPE (mm): 66.5 -> 51.6 | Improved |
| add Collaborative Evolution Enhancer (ablation) | CoEvoer · UBody (hand) | MPVPE (mm): 36.9 -> 27.8 | Improved |
| add Portrait Foreground Extraction (ablation) | CoEvoer · UBody (all) | MPVPE (mm): 54.4 -> 51.6 | Improved |
| add Portrait Foreground Extraction (ablation) | CoEvoer · UBody (hand) | PA-MPVPE (mm): 9.4 -> 7.1 | Improved |
| add Portrait Foreground Extraction (ablation) | CoEvoer · UBody (face) | PA-MPVPE (mm): 2.1 -> 1.8 | Improved |
| CoEvoer versus OSX on full-body AGORA | CoEvoer · AGORA (face PA-MPVPE) | PA-MPVPE (mm): 4.8 -> 4.7 | No clear effect |
| CoEvoer versus OSX on EHF hand | CoEvoer · EHF (hand MPVPE) | MPVPE (mm): H4W 39.8 vs Ours 48.9 | Hurt |
| add cross-part interaction from upper body to full-body settings | CoEvoer · AGORA / EHF (all) | MPVPE (mm): 168.6 -> 160.8 (AGORA), 70.8 -> 66.3 (EHF) vs OSX | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- AiOS — AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation (CVPR 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation (NeurIPS 2023 · similarity 0.88)
- SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation (TPAMI 2025 · similarity 0.87)
- Monocular Expressive Body Regression through Body-Driven Attention (ECCV 2020 · similarity 0.87)
- COAP: Compositional Articulated Occupancy of People (CVPR 2022 · similarity 0.86)
- AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation (CVPR 2024 · similarity 0.86)
- HiPoser: 3D Human Pose Estimation with Hierarchical Shared Learning at Parts-Level Using Inertial Measurement Units (AAAI 2025 · 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.
