Generative Adversarial Network-based Image Super-Resolution with a Novel Quality Loss
Xining Zhu, Zhang Lin, Lijun Zhang, Xiao Liu, Ying Shen, Shengjie Zhao · 2019
Single Image Super-Resolution (SISR) has been a very attractive research topic in recent years. Breakthroughs in SISR have been achieved due to deep learning and Generative Adversarial Networks (GANs). However, the generated image still suffers from undesired artifacts. In this paper, we propose a new method named GMGAN for SISR tasks. In this method, to generate images more in line with Human Vision System (HVS), we design a quality loss by integrating an IQA metric named Gradient Magnitude Similarity Deviation (GMSD). To our knowledge, it is the first time to truly integrate an IQA metric into SISR. Moreover, to overcome the instability of the original GAN, we use a variation of GANs named WGAN-GP. Experiments show that GMGAN with quality loss and WGAN-GP can generate visually appealing results and set a new state-of-art.