Deep Learning Based Single Image Super-Resolution: A Survey

Ha, Viet Khanh; Ren, Jinchang; Xu, Xinying; Zhao, Sophia; Xie, Gang; Vargas, Valentin Masero

Abstract

Image super-resolution is a process of obtaining one or more high-resolution image from single or multiple samples of low-resolution images. Due to its wide applications, a number of different techniques have been developed recently, including interpolation-based, reconstruction-based and learning-based. The learning-based methods have recently attracted increasing great attention due to their capability in predicting the high-frequency details lost in low resolution image. This survey mainly provides an overview on most of published work for single image reconstruction using Convolutional Neural Network. Furthermore, common issues in super-resolution algorithms, such as imaging models, improvement factor and assessment criteria are also discussed.

Citation

HA, V.K., REN, J., XU, X., ZHAO, S. XIE, G. and VARGAS, V.M. 2018. Deep learning based single image super-resolution: a survey. In Ren, J., Hussain, A., Zheng, J., Liu, C.-L., Luo, B., Zhao, H. and Zhao, X. (eds.) Advances in brain inspired cognitive systems: proceedings of 9th International conference brain inspired cognitive systems 2018 (BICS 2018), 7-8 July 2018, Xi'an, China. Lecture notes in computer sciences, 10989. Cham: Springer [online], pages 106-119. Available from: https://doi.org/10.1007/978-3-030-00563-4_11

• Conference Name: 9th International conference brain inspired cognitive systems 2018 (BICS 2018)
• Conference Location: Xi'an, China
• Start Date: Jul 7, 2018
• End Date: Jul 8, 2018
• Acceptance Date: May 31, 2018
• Online Publication Date: Oct 6, 2018
• Publication Date: Dec 31, 2018
• Deposit Date: Jun 30, 2022
• Publicly Available Date: Jun 30, 2022
• Publisher: Springer
• Pages: 106-119
• Series Title: Lecture notes in computer science
• Series Number: 10989
• Book Title: Advances in brain inspired cognitive systems: proceedings of 9th International conference brain inspired cognitive systems 2018 (BICS 2018)
• ISBN: 9783030005627
• DOI: https://doi.org/10.1007/978-3-030-00563-4_11
• Keywords: Image super resolution; Convolutional neural network; High-resolution image
• Public URL: https://rgu-repository.worktribe.com/output/1699376