CoMoGAN: Continuous Model-Guided Image-to-Image Translation

Fabio Pizzati, Pietro Cerri, Raoul de Charette

CVPR 2021 pp. 14288-14298

doi:10.1109/CVPR46437.2021.01406 /cvpr/2021/pizzati2021cvpr-comogan/

Abstract

CoMoGAN is a continuous GAN relying on the unsupervised reorganization of the target data on a functional manifold. To that matter, we introduce a new Functional Instance Normalization layer and residual mechanism, which together disentangle image content from position on target manifold. We rely on naive physics-inspired models to guide the training while allowing private model/translations features. CoMoGAN can be used with any GAN backbone and allows new types of image translation, such as cyclic image translation like timelapse generation, or detached linear translation. On all datasets, it outperforms the literature. Our code is available in this page: https://github.com/cv-rits/CoMoGAN.

PDF CVPR Semantic Scholar

Cite

Text

Pizzati et al. "CoMoGAN: Continuous Model-Guided Image-to-Image Translation." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.01406

Markdown

[Pizzati et al. "CoMoGAN: Continuous Model-Guided Image-to-Image Translation." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/pizzati2021cvpr-comogan/) doi:10.1109/CVPR46437.2021.01406

BibTeX

@inproceedings{pizzati2021cvpr-comogan,
  title     = {{CoMoGAN: Continuous Model-Guided Image-to-Image Translation}},
  author    = {Pizzati, Fabio and Cerri, Pietro and de Charette, Raoul},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2021},
  pages     = {14288-14298},
  doi       = {10.1109/CVPR46437.2021.01406},
  url       = {https://mlanthology.org/cvpr/2021/pizzati2021cvpr-comogan/}
}