High-Resolution GAN Inversion for Degraded Images in Large Diverse Datasets

by   Yanbo Wang, et al.

The last decades are marked by massive and diverse image data, which shows increasingly high resolution and quality. However, some images we obtained may be corrupted, affecting the perception and the application of downstream tasks. A generic method for generating a high-quality image from the degraded one is in demand. In this paper, we present a novel GAN inversion framework that utilizes the powerful generative ability of StyleGAN-XL for this problem. To ease the inversion challenge with StyleGAN-XL, Clustering & Regularize Inversion (CRI) is proposed. Specifically, the latent space is firstly divided into finer-grained sub-spaces by clustering. Instead of initializing the inversion with the average latent vector, we approximate a centroid latent vector from the clusters, which generates an image close to the input image. Then, an offset with a regularization term is introduced to keep the inverted latent vector within a certain range. We validate our CRI scheme on multiple restoration tasks (i.e., inpainting, colorization, and super-resolution) of complex natural images, and show preferable quantitative and qualitative results. We further demonstrate our technique is robust in terms of data and different GAN models. To our best knowledge, we are the first to adopt StyleGAN-XL for generating high-quality natural images from diverse degraded inputs. Code is available at https://github.com/Booooooooooo/CRI.


page 2

page 5

page 6

page 7


Creating High Resolution Images with a Latent Adversarial Generator

Generating realistic images is difficult, and many formulations for this...

Latent Convolutional Models

We present a new latent model of natural images that can be learned on l...

QC-StyleGAN – Quality Controllable Image Generation and Manipulation

The introduction of high-quality image generation models, particularly t...

Semantic-Aware Latent Space Exploration for Face Image Restoration

For image restoration, most existing deep learning based methods tend to...

Aligning Latent and Image Spaces to Connect the Unconnectable

In this work, we develop a method to generate infinite high-resolution i...

High-Fidelity Image Inpainting with GAN Inversion

Image inpainting seeks a semantically consistent way to recover the corr...

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation

Learning a good image prior is a long-term goal for image restoration an...

Please sign up or login with your details

Forgot password? Click here to reset