A Geometric and Photometric Exploration of GAN and Diffusion Synthesized Faces

Abstract

Classic computer-generated imagery is produced by modeling 3D scene geometry, the surrounding illumination, and a virtual camera. As a result, rendered images accurately capture the geometry and physics of natural scenes. In contrast, AI-generated imagery is produced by learning the statistical distribution of natural scenes from a large set of real images. Without an explicit 3D model of the world, we wondered how accurately synthesized content captures the 3D geometric and photometric properties of natural scenes. From a diverse set of real, GAN- and diffusion-synthesized faces, we estimate a 3D geometric model of the face, from which we estimate the surrounding 3D photometric environment. We also analyze 2D facial features – eyes and mouth – that have been traditionally difficult to accurately render. Using these models, we provide a quantitative analysis of the 3D and 2D realism of synthesized faces.

Cite

Text

Bohácek and Farid. "A Geometric and Photometric Exploration of GAN and Diffusion Synthesized Faces." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00094

Markdown

[Bohácek and Farid. "A Geometric and Photometric Exploration of GAN and Diffusion Synthesized Faces." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/bohacek2023cvprw-geometric/) doi:10.1109/CVPRW59228.2023.00094

BibTeX

@inproceedings{bohacek2023cvprw-geometric,
  title     = {{A Geometric and Photometric Exploration of GAN and Diffusion Synthesized Faces}},
  author    = {Bohácek, Matyás and Farid, Hany},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2023},
  pages     = {874-883},
  doi       = {10.1109/CVPRW59228.2023.00094},
  url       = {https://mlanthology.org/cvprw/2023/bohacek2023cvprw-geometric/}
}