Quaffure: Real-Time Quasi-Static Neural Hair Simulation

Abstract

Realistic hair motion is crucial for high-quality avatars, but it is often limited by the computational resources available for real-time applications. To address this challenge, we propose a novel neural approach to predict physically plausible hair deformations that generalizes to various body poses, shapes, and hair styles. Our model is trained using a self-supervised loss, eliminating the need for expensive data generation and storage. We demonstrate our method's effectiveness through numerous results across a wide range of pose and shape variations, showcasing its robust generalization capabilities and temporally smooth results. Our approach is highly suitable for real-time applications with an inference time of only a few milliseconds on consumer hardware and its ability to scale to predicting 1000 grooms in 0.3 seconds. Code will be released.

Cite

Text

Stuyck et al. "Quaffure: Real-Time Quasi-Static Neural Hair Simulation." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.00031

Markdown

[Stuyck et al. "Quaffure: Real-Time Quasi-Static Neural Hair Simulation." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/stuyck2025cvpr-quaffure/) doi:10.1109/CVPR52734.2025.00031

BibTeX

@inproceedings{stuyck2025cvpr-quaffure,
  title     = {{Quaffure: Real-Time Quasi-Static Neural Hair Simulation}},
  author    = {Stuyck, Tuur and Lin, Gene Wei-Chin and Larionov, Egor and Chen, Hsiao-yu and Bozic, Aljaz and Sarafianos, Nikolaos and Roble, Doug},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2025},
  pages     = {239-249},
  doi       = {10.1109/CVPR52734.2025.00031},
  url       = {https://mlanthology.org/cvpr/2025/stuyck2025cvpr-quaffure/}
}