SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery
TL;DR: SKEL-CF is a coarse-to-fine transformer framework for estimating anatomically accurate SKEL parameters from 3D human data. By converting 4DHuman to SKEL-aligned 4DHuman-SKEL and incorporating camera modeling, it addresses data scarcity and depth/scale ambiguities. SKEL-CF outperforms prior SKEL-based methods on MOYO (85.0 MPJPE / 51.4 PA-MPJPE), offering a scalable, biomechanically faithful solution for human motion analysis.
Model Sources
- Repository: Intellindust-AI-Lab/SKEL-CF
- Paper (Hugging Face): SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery
- Paper (arXiv): SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery
- Project Page: SKEL-CF Project Page
- Demo: Github Demo
ποΈ Updates
- [2025.11.26] Release SKEL-CF.
- [2025.11.27] Release checkpoints and labels on Hugging Face.
π§ Table of Content
- 1. βοΈ Setup
- 2. π Demo & Quick Start
- 3. π§± Reproducibility
- 4. π Visual Results
- 5. π Citation
- 6. π Acknowledgement
- 7. π Star History
βοΈ Setup
π Quick Start
Quick start with images:
bash vis/run_demo.sh
Quick start with videos:
bash vis/run_video.sh
π§± Reproducibility
For reproducing the results in the paper, please refer to docs/EVAL.md and docs/TRAIN.md.
π Visual Results
Per-Layer Refinement
Sports Video
π‘ Tip: Click the buttons above to watch videos, or visit our project page for more visual results.
π Citation
If you use SKEL-CF or its methods in your work, please cite the following BibTeX entries:
@article{li2025skelcf,
title={SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery},
author={Li, Da and Jin, Jiping and Yu, Xuanlong and Cun, Xiaodong and Chen, Kai and Fan, Rui and Kong, Jiangang and Shen, Xi},
journal={arXiv},
year={2025}
}
π Acknowledgement
Parts of the code are adapted from the following repos: SKEL, CameraHMR, HSMR, ViTPose, Detectron2

