Difference Value Network for Image Super-Resolution

作     者：Jiang, Zetao Pi, Kui Huang, Yongsong Qian, Yi Zhang, Shaoqin 

作者机构：Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc Guilin 541004 Peoples R China Nanchang Hangkong Univ Nanchang 330063 Jiangxi Peoples R China 

出 版 物：《IEEE SIGNAL PROCESSING LETTERS》 (IEEE Signal Process Lett)

年 卷 期：2021年第28卷

页      面：1070-1074页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 

基　　金：National Natural Science Foundation of China [61876049, 61762066] Guangxi Key Laboratory of Image Innovation Project of Guangxi Graduate Education [2019YCXS043, YCBZ2018052, YCBZ2021070] Innovation Project of GUET Graduate Education [2020YCXS050, 2021YCXS071] Graphic Intelligent Processing [GIIP2007, GIIP2008] 

主　　题：Image reconstruction Feature extraction Convolution Superresolution Training Graphics Correlation Image super-resolution deep convolutional neural networks adjacent layers difference value 

摘      要：Recently, improved performance has been achieved in image super-resolution (SR) by using deep convolutional neural networks (CNNs). However, most existing networks neglect the feature correlations of adjacent layers, causing features at different levels to not be fully utilized. In this paper, a novel difference value network (DVN) is proposed to address this problem. The proposed network makes full use of different levels of features by using the difference values (D-values) of adjacent layers. Specifically, a difference value block (DVB) is designed to extract the difference values of adjacent layers. The extracted difference value can highlight which regions should be paid more attention to, so as to guide image SR. Further, a difference value group (DVG) is designed to integrate the difference values extracted by the difference value block into its output. In this way, the DVG can provide additional structure prior for image SR. Finally, to make our network more stable, a multipath supervised reconstruction block is proposed to supervise the reconstruction process. The experimental results on five benchmark datasets show that the proposed network can achieve better reconstruction results than the compared SR methods.