Timezone: »

 
Poster
QC-StyleGAN - Quality Controllable Image Generation and Manipulation
Dat Viet Thanh Nguyen · Phong Tran The · Tan M. Dinh · Cuong Pham · Anh Tran

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #637

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.

Author Information

Dat Viet Thanh Nguyen (VinAI Research)
Phong Tran The (MBZUAI)
Tan M. Dinh (VinAI Research)
Cuong Pham (Posts & Telecommunications Institute of Technology and VinAI Research)

I am an Associate Professor of Computer Science at Posts and Telecommunications Institute of Technology (PTIT) and a Visiting Research Scientist at VinAI Research. I am also a Vice Dean of Information Technology faculty and the Director of NAVER AI Research Lab., PTIT. Previously, I was a Marie Curie Research Fellow at Philips Research, High-Tech campus Eindhoven, the Netherlands; a Research Associate at Open Lab, Newcastle University, UK; a Research Assistant at Jornada Experimental Range, the United State Department of Agriculture, USA; and a Teaching Assistant at PTIT. My research interests include Ubiquitous Computing, Sensing Technologies, Computer Vision, Human Activity Recognition, Machine Learning, and Pervasive Healthcare.

Anh Tran (VinAI Research)

More from the Same Authors