SR-AFU: super-resolution network using adaptive frequency component upsampling and multi-resolution features  

作　　者：Ke-Jia CHEN Mingyu WU Yibo ZHANG Zhiwei CHEN 

机构地区：[1]School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China [2]Jiangsu Key Laboratory of Big Data Security&Intelligent Processing,Nanjing University of Posts and Telecommunications,Nanjing 210023,China [3]College of Telecommunications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China

出　　处：《Frontiers of Computer Science》2023年第1期123-132,共10页中国计算机科学前沿（英文版）

基　　金：supported by the National Natural Science Foundation of China(Grant Nos.61603197 and 61772284);Natural Science Foundation of Nanjing University of Posts and Telecommunications(NY221071).

摘　　要：Image super-resolution (SR) is one of the classic computer vision tasks. This paper proposes a super-resolution network based on adaptive frequency component upsampling, named SR-AFU. The network is composed of multiple cascaded dilated convolution residual blocks (CDCRB) to extract multi-resolution features representing image semantics, and multiple multi-size convolutional upsampling blocks (MCUB) to adaptively upsample different frequency components using CDCRB features. The paper also defines a new loss function based on the discrete wavelet transform, making the reconstructed SR images closer to human perception. Experiments on the benchmark datasets show that SR-AFU has higher peak signal to noise ratio (PSNR), significantly faster training speed and more realistic visual effects compared with the existing methods.

关 键 词：SUPER-RESOLUTION multi-resolution features adaptive frequency upsampling wavelet transformation 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]