QC-StyleGAN -- Quality Controllable Image Generation and Manipulation

Autor:	Nguyen, Dat Viet Thanh, The, Phong Tran, Dinh, Tan M., Pham, Cuong, Tran, Anh Tuan
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted to NeurIPS 2022; The code is available at https://github.com/VinAIResearch/QC-StyleGAN
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2212.00981 Zobrazit plný text záznamu View this record from Arxiv