Research map / 3D vision / Human pose estimation
One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer
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 |
|---|---|---|---|
| Replace separate component pipelines with one-stage OSX | Whole-body mesh recovery · AGORA-test | MPVPE All (mm): 135.5 -> 122.8 | Helped |
| Replace separate component pipelines with one-stage OSX | Whole-body mesh recovery · EHF | MPVPE All (mm): 76.8 -> 70.8 | Helped |
| Replace separate component pipelines with one-stage OSX | Body mesh recovery · 3DPW | MPJPE Body (mm): 86.6 -> 74.7 | Helped |
| Fine-tune OSX on UBody training data | OSX · UBody intra-scene test | MPVPE All (mm): 92.4 -> 81.9 | Helped |
| Add the hand decoder (ablation) | OSX · EHF | Hand MPVPE (mm): 55.3 -> 53.7 | Helped |
| Add keypoint-guided scheme to the hand decoder (ablation) | OSX · EHF | Hand MPVPE (mm): 55.1 -> 53.7 | Helped |
| Add both the hand decoder and keypoint-guided scheme (ablation) | OSX · EHF | Hand MPVPE (mm): 56.4 -> 53.7 | Helped |
| Add the face decoder (ablation) | OSX · EHF | Face MPVPE (mm): 27.2 -> 26.4 | Helped |
| Add keypoint-guided scheme to the face decoder (ablation) | OSX · EHF | Face MPVPE (mm): 26.4 -> 26.4 | No clear effect |
| Add both the face decoder and keypoint-guided scheme (ablation) | OSX · EHF | Face MPVPE (mm): 26.8 -> 26.4 | Helped |
| Increase feature upsampling scale from ×1 to ×4 (ablation) | OSX · EHF | Hand MPVPE (mm): 54.9 -> 53.7 | Helped |
| Increase feature upsampling scale from ×4 to ×8 (ablation) | OSX · EHF | Hand MPVPE (mm): 53.7 -> 54.1 | Hurt |
Closest papers by meaning
- AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation (CVPR 2024 · similarity 0.89)
- BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation (CVPR 2025 · similarity 0.88)
- Reconstructing Hands in 3D with Transformers (CVPR 2024 · similarity 0.87)
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.87)
- FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery (NeurIPS 2026 · similarity 0.86)
- Reconstructing Humans with a Biomechanically Accurate Skeleton (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.