QC-StyleGAN -- Quality Controllable Image Generation and Manipulation

TL;DR

QC-StyleGAN introduces a novel GAN architecture that enables controllable image quality generation and restoration, allowing direct editing of low-quality images and handling various degradations.

Contribution

It presents a new GAN model capable of generating and restoring images with controllable quality levels, addressing the gap for low-quality image manipulation.

Findings

Can generate images with adjustable quality levels.

Effectively restores low-quality images with various degradations.

Enables applications like degradation synthesis and transfer.

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. The code is available at https://github.com/VinAIResearch/QC-StyleGAN.