QC-StyleGAN -- Quality Controllable Image Generation and Manipulation
This work addresses the challenge of handling in-the-wild low-quality images for image generation and manipulation, which is incremental by extending StyleGAN capabilities to quality control.
The paper tackles the problem of generating and manipulating images with controllable quality, enabling direct editing of low-quality images without altering their degradation, and achieves this by proposing a novel GAN structure that synthesizes various degradations and restores sharp images via a quality control code.
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.