Robust Unsupervised StyleGAN Image Restoration
Yohan Poirier-Ginter     Jean-François Lalonde    




[Paper]
[Supp.]
[GitHub]
[Video]

Presented at CVPR, 2023!


Abstract

GAN-based image restoration inverts the generative process to repair images corrupted by known degrada- tions. Existing unsupervised methods must be carefully tuned for each task and degradation level. In this work, we make StyleGAN image restoration robust: a single set of hyperparameters works across a wide range of degradation levels. This makes it possible to handle combinations of several degradations, without the need to retune. Our proposed approach relies on a 3-phase progressive latent space extension and a conservative optimizer, which avoids the need for any additional reg- ularization terms. Extensive experiments demonstrate robustness on inpainting, upsampling, denoising, and deartifacting at varying degradations levels, outperform- ing other StyleGAN-based inversion techniques. Our approach also favorably compares to diffusion-based restoration by yielding much more realistic inversion results.


Paper and Supplementary Material

Yohan Poirier-Ginter, Jean-François Lalonde
Robust Unsupervised StyleGAN Image Restoration
(hosted on ArXiv)


[Bibtex]

Poster


click on the figure to see .pdf version.




Acknowledgements

This research was supported by NSERC grant RGPIN-2020-04799, and by Compute Canada.