Robust Unsupervised StyleGAN Image Restoration
This work addresses the need for more adaptable and efficient unsupervised image restoration tools for computer vision applications, though it is incremental as it builds on existing StyleGAN inversion methods.
The paper tackles the problem of making StyleGAN-based image restoration robust across varying degradation levels without task-specific tuning, achieving a single hyperparameter set that works for multiple degradations like inpainting and denoising, and outperforms other inversion techniques while yielding more realistic results than diffusion-based methods.
GAN-based image restoration inverts the generative process to repair images corrupted by known degradations. 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 regularization terms. Extensive experiments demonstrate robustness on inpainting, upsampling, denoising, and deartifacting at varying degradations levels, outperforming other StyleGAN-based inversion techniques. Our approach also favorably compares to diffusion-based restoration by yielding much more realistic inversion results. Code is available at https://lvsn.github.io/RobustUnsupervised/.