Fast and accurate single image super-resolution via an energy-aware improved deep residual network

• Published in: Signal processing 2019-09, Vol.162, p.115-125
• Main Authors: Cao, Yanpeng, He, Zewei, Ye, Zhangyu, Li, Xin, Cao, Yanlong, Yang, Jiangxin
• Format: Article
• Language: English
• Subjects: Energy aware; Loss function; Residual network; Skip connections; Super-resolution
• ISSN: 0165-1684; 1872-7557
• DOI: 10.1016/j.sigpro.2019.03.018

•We propose a novel energy-aware loss function for single image super-resolution.•A modified structure of residual network is applied to increase performance.•Our EA-IDRN achieves higher accuracy and significantly faster running speed than alternatives. Recently, convolutional neural network (CNN) based single image super-resolution (SISR) solutions have demonstrated significant progress on restoring accurate high-resolution image based on its corresponding low-resolution version. However, most state-of-the-art SISR approaches attempt to achieve higher accuracy by pursuing deeper or more complicated models, which adversely increases computational cost. To achieve a good balance between restoration accuracy and computational speed, we make simple but effective modifications to the structure of residual blocks and skip-connections between stacked layers, and then propose a novel energy-aware training loss to adaptively adjust the restoration of high-frequency and low-frequency image regions. Extensive qualitative and quantitative evaluation results on benchmark datasets verify the effectiveness of the proposed techniques that they significantly improve SISR accuracy while causing no/ignorable extra computational loads.