Image Super-Resolution Using Complex Dense Block on Generative Adversarial Networks

• Published in: Proceedings - International Conference on Image Processing pp. 2866 - 2870
• Main Authors: Chen, Bo-Xun, Liu, Tsung-Jung, Liu, Kuan-Hsien, Liu, Hsin-Hua, Pei, Soo-Chang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2019
• Subjects: dense block; Feature extraction; generative adversarial network (GAN); Generative adversarial networks; Generators; Image resolution; Network architecture; Signal resolution; Super-resolution (SR); visual quality; Visualization
• ISSN: 2381-8549
• DOI: 10.1109/ICIP.2019.8803711

The recent super-resolution (SR) techniques are divided into two directions. One is to improve PSNR and the other is to improve visual quality. We believe improving visual quality is more important and practical than blindly improving PSNR. In this paper we employ a generative adversarial network (GAN) and a new perceptual loss function for photo-realistic single image super-resolution (SISR). Our main contributions are as follows: we propose a new dense block which uses complex connections between each layer to build a more powerful generator. Next, to improve the perceptual quality, we found a new set of feature maps to compute the perceptual loss, which would make the output image look more real and natural. Finally, we compare our results with other methods by subjective evaluation. The subjects rank the image generated by various methods from good to bad. The final results show that our method can generate a more natural and realistic SR image than other state-of-the-art methods.