Research map / 3D vision / Human pose estimation
Skeleton2Mesh: Kinematics Prior Injected Unsupervised Human Mesh Recovery
Zhenbo Yu, Junjie Wang, Jingwei Xu, Bingbing Ni, Chenglong Zhao, Minsi Wang, Wenjun Zhang
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 differentiable inverse kinematics (DIK) instead of learned pose regression (ablation) | Skeleton2Mesh · Human3.6M test | PMPJPE: 111.9 -> 55.4 | Improved |
| use DIK instead of iterative IK solver (ablation) | Skeleton2Mesh · Human3.6M | mean joint angle error: 0.592 -> 0.391 | Improved |
| add adaptive joint regressor (ablation) | Skeleton2Mesh · Human3.6M test | PMPJPE: 63.7 -> 55.4 | Improved |
| add shape refinement (differentiable renderer) (ablation) | Skeleton2Mesh · Human3.6M test | PVE: 122.6 -> 120.8 | Improved |
| add shape refinement (differentiable renderer) (ablation) | Skeleton2Mesh · Surreal val | PVE: 112.9 -> 107.8 | Improved |
| add shape refinement (differentiable renderer) (ablation) | Skeleton2Mesh · Surreal val | MPJPE: 95.1 -> 99.5 | Hurt |
| add pose refinement (PR) module (ablation) | Skeleton2Mesh · Surreal val | PPVE: 82.5 -> 75.1 | Improved |
| add pose refinement (PR) module (ablation) | Skeleton2Mesh · Human3.6M test | PPVE: 81.4 -> 80.8 | Improved |
| add pose refinement (PR) module (ablation) | Skeleton2Mesh · Surreal val | joint angle error: 0.325 -> 0.314 | Improved |
| refine all local rotations instead of only endpoint rotations in PR (ablation) | Skeleton2Mesh DIK+PR · Human3.6M | mean joint angle error: 0.389 -> 0.404 | Hurt |
| apply temporal correction to discontinuous frames | Skeleton2Mesh · Human3.6M | PPVE: 81.98 -> 69.70 | Improved |
Later papers that compared with this method
1 later accepted paper reports Skeleton2Mesh as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Self-supervised Human Mesh Recovery with Cross-Representation Alignment (ECCV 2022 · better on 2 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
- Reconstructing Humans with a Biomechanically Accurate Skeleton (CVPR 2025 · similarity 0.91)
- TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation (CVPR 2024 · similarity 0.90)
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.89)
- FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery (NeurIPS 2026 · similarity 0.89)
- BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation (CVPR 2025 · similarity 0.89)
- GenHMR: Generative Human Mesh Recovery (AAAI 2025 · similarity 0.89)
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.
