QC-StyleGAN - Quality Controllable Image Generation and ManipulationDownload PDF

Published: 31 Oct 2022, Last Modified: 05 May 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: StyleGAN, GAN Inversion, Image restoration, Image Generation, Image Manipulation, Image Editing, Degradation Synthesis
TL;DR: We propose a novel StyleGAN structure with a direct quality control input that bridges the sharp and degraded image domains, allowing many applications.
Abstract: The introduction of high-quality image generation models, particularly the StyleGAN family, provides a powerful tool to synthesize and manipulate images. However, existing models are built upon high-quality (HQ) data as desired outputs, making them unfit for in-the-wild low-quality (LQ) images, which are common inputs for manipulation. In this work, we bridge this gap by proposing a novel GAN structure that allows for generating images with controllable quality. The network can synthesize various image degradation and restore the sharp image via a quality control code. Our proposed QC-StyleGAN can directly edit LQ images without altering their quality by applying GAN inversion and manipulation techniques. It also provides for free an image restoration solution that can handle various degradations, including noise, blur, compression artifacts, and their mixtures. Finally, we demonstrate numerous other applications such as image degradation synthesis, transfer, and interpolation.
Supplementary Material: pdf
20 Replies