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.

SKEL-CF Teaser Image

Model Sources


πŸ—“οΈ Updates

  • [2025.11.26] Release SKEL-CF.
  • [2025.11.27] Release checkpoints and labels on Hugging Face.

🧭 Table of Content

βš’οΈ Setup

  1. 🌏 Environment Setup
  2. πŸ“¦ Data Preparation

πŸš€ Quick Start

Quick start with images:

bash vis/run_demo.sh

Quick start with videos:

bash vis/run_video.sh

🧱 Reproducibility

For reproducing the results in the paper, please refer to docs/EVAL.md and docs/TRAIN.md.

πŸ‘€ Visual Results

Per-Layer Refinement

Per-Layer Refinement 2 Per-Layer Refinement 1

Sports Video

Badminton Video Skate Video

πŸ’‘ Tip: Click the buttons above to watch videos, or visit our project page for more visual results.

πŸ“ 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}
}

πŸ“œ Acknowledgement

Parts of the code are adapted from the following repos: SKEL, CameraHMR, HSMR, ViTPose, Detectron2

🌟 Star History

Star History Chart

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support