Monocular Facial Appearance Capture in the Wild

Abstract

We present a new method for reconstructing the appearance properties of human faces from a lightweight capture procedure in an unconstrained environment. Our method recovers the surface geometry, diffuse albedo, specular intensity and specular roughness from a monocular video containing a simple head rotation in-the-wild. Notably, we make no simplifying assumptions on the environment lighting, and we explicitly take visibility and occlusions into account. As a result, our method can produce facial appearance maps that approach the fidelity of studio-based multi-view captures, but with a far easier and cheaper procedure.

Cite

Text

Xu et al. "Monocular Facial Appearance Capture in the Wild." International Conference on Computer Vision, 2025.

Markdown

[Xu et al. "Monocular Facial Appearance Capture in the Wild." International Conference on Computer Vision, 2025.](https://mlanthology.org/iccv/2025/xu2025iccv-monocular/)

BibTeX

@inproceedings{xu2025iccv-monocular,
  title     = {{Monocular Facial Appearance Capture in the Wild}},
  author    = {Xu, Yingyan and Gadola, Kate and Chandran, Prashanth and Weiss, Sebastian and Gross, Markus and Zoss, Gaspard and Bradley, Derek},
  booktitle = {International Conference on Computer Vision},
  year      = {2025},
  pages     = {12078-12088},
  url       = {https://mlanthology.org/iccv/2025/xu2025iccv-monocular/}
}