Title: Exploring real-time super-resolution generative adversarial networks

Authors: Xiaoyan Hu; Zechen Wang; Xiangjun Liu; Xinran Li; Guang Cheng; Jian Gong

Addresses: School of Cyber Science and Engineering, Southeast University, Nanjing, 211189, China; Key Laboratory of Computer Network and Information Integration, Southeast University, Ministry of Education, Nanjing 211189, China; Purple Mountain Laboratories for Network and Communication Security, Nanjing 211111, China ' School of Computer Science and Engineering, Southeast University, Nanjing, 211189, China ' State Key Lab of Novel Software Technology, Nanjing University, Nanjing, 210093, China ' School of Computer Science and Engineering, Southeast University, Nanjing, 211189, China ' School of Cyber Science and Engineering, Southeast University, Nanjing, 211189, China ' School of Cyber Science and Engineering, Southeast University, Nanjing, 211189, China

Abstract: Image super-resolution is an essential technology for improving user quality of experience of internet videos. As the state-of-the-art deep learning-based super-resolution technology, the enhanced super-resolution generative adversarial networks (ESRGAN) has the best performance in the perceptual quality of reconstructed images, and the efficient sub-pixel convolutional neural network (ESPCN) has the best real-time performance. This work proposes real-time super-resolution generative adversarial network (RTSRGAN). RTSRGAN takes the advantages of ESRGAN and ESPCN so as to simultaneously satisfy the demands on the real-time performance and the resulting pleasant artifacts of super-resolution at the client side. Our experimental studies demonstrate our proposed RTSRGAN can be used for super-resolution at the client side to enhance the real-time performance as well as ensure the image perceptual quality.We also find that RTSRGAN is suitable for restoring imageswith regularly changing texture featureswithout requiring training for individual image categories.

Keywords: image super-resolution; real-time; ESRGAN; enhanced super-resolution generative adversarial networks; ESPCN' efficient sub-pixel convolutional neural network; efficient sub-pixel convolutional; network Structure.

DOI: 10.1504/IJSNET.2021.115917

International Journal of Sensor Networks, 2021 Vol.36 No.2, pp.85 - 96

Received: 17 Dec 2020
Accepted: 23 Dec 2020
Published online: 05 Jul 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article