Research map / 3D vision / Human pose estimation
Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video
Yingxuan You, Hong Liu, Ti Wang, Wenhao Li, Runwei Ding, Xia Li
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 |
|---|---|---|---|
| normalize 2D pose with respect to the full image rather than cropped box (ablation) | PMCE 3D pose stream · Human3.6M | MPJPE: 58.2 -> 53.5 | Improved |
| add bounding box info to cropped pose (ablation) | PMCE 3D pose stream · Human3.6M | MPJPE: 58.2 -> 56.4 | Improved |
| use sequence input instead of single frame (ablation) | PMCE · Human3.6M | ACCEL: 17.9 -> 3.1 | Improved |
| add image features in both encoder and decoder (ablation) | PMCE · 3DPW | MPJPE (output mesh): 76.9 -> 69.5 | Improved |
| add pose->mesh interaction (ablation) | PMCE decoder · 3DPW | MPJPE (output mesh): 72.3 -> 70.8 | Improved |
| add mesh->pose interaction (ablation) | PMCE decoder · 3DPW | MPJPE (output pose): 70.6 -> 68.8 | Improved |
| use bi-directional pose-mesh interaction (ablation) | PMCE decoder · 3DPW | MPJPE (output mesh): 72.3 -> 69.5 | Improved |
| use AdaLN instead of LN (ablation) | PMCE decoder · 3DPW | MPJPE (output mesh): 72.0 -> 69.5 | Improved |
| use AdaLN instead of SEAN (ablation) | PMCE decoder · 3DPW | MPJPE (output mesh): 70.5 -> 69.5 | Improved |
| increase input sequence length | PMCE · Human3.6M | PA-MPJPE and ACCEL | Improved |
| use more accurate 2D pose detector (CPN vs SH) (ablation) | PMCE · Human3.6M | MPJPE: 56.4 -> 53.5 | Improved |
| use PMCE rather than MAED with ViT backbone | video mesh recovery · 3DPW | MPJPE: 79.1 -> 69.5 | Improved |
Closest papers by meaning
- Uncertainty-Aware Human Mesh Recovery From Video by Learning Part-Based 3D Dynamics (ICCV 2021 · similarity 0.91)
- End-to-End Recovery of Human Shape and Pose (CVPR 2018 · similarity 0.90)
- PHD: Personalized 3D Human Body Fitting with Point Diffusion (ICCV 2025 · similarity 0.90)
- Capturing the Motion of Every Joint: 3D Human Pose and Shape Estimation with Independent Tokens (ICLR 2023 · similarity 0.90)
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.88)
- TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation (CVPR 2024 · similarity 0.88)
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.
