GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling

Yang Zheng1,2     Menglei Chai2     Delio Vicini2     Yuxiao Zhou2,3     Yinghao Xu1     Leonidas Guibas1     Gordon Wetzstein1     Thabo Beeler2    
1Stanford University, 2Google, 3ETH Zurich
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Teaser

GroomLight achieves high-fidelity reconstruction of human hair appearance from real-world images, enabling realistic rendering under diverse lighting conditions. Here, in each column, we present relighting results of a same subject under two different environments, using the appearance model reconstructed by GroomLight. One input view with the similar head pose is shown at the top right corner.

Abstract

We present GroomLight, a novel method for relightable hair appearance modeling from multi-view images. Existing hair capture methods struggle to balance photorealistic rendering with relighting capabilities. Analytical material models, while physically grounded, often fail to fully capture appearance details. Conversely, neural rendering approaches excel at view synthesis but generalize poorly to novel lighting conditions. GroomLight addresses this challenge by combining the strengths of both paradigms. It employs an extended hair BSDF model to capture primary light transport and a light-aware residual model to reconstruct the remaining details. We further propose a hybrid inverse rendering pipeline to optimize both components, enabling high-fidelity relighting, view synthesis, and material editing. Extensive evaluations on real-world hair data demonstrate state-of-the-art performance of our method.

Downloads & resources

Text Reference Copy to clipboard

Yang Zheng, Menglei Chai, Delio Vicini, Yuxiao Zhou, Yinghao Xu, Leonidas Guibas, Gordon Wetzstein, Thabo Beeler. GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

BibTex Reference Copy to clipboard

@inproceedings{Zheng2025GroomLight,
    title        = {GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling},
    author       = {Yang Zheng and Menglei Chai and Delio Vicini and Yuxiao Zhou and Yinghao Xu and Leonidas Guibas and Gordon Wetzstein and Thabo Beeler},
    doi          = {10.48550/arXiv.2503.10597},
    year         = 2025,
    booktitle    = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
}