Dually Connected Deraining Net Using Pixel-Wise Attention

作     者：Ren, Weihong Tian, Jiandong Wang, Qiang Tang, Yandong 

作者机构：Chinese Acad Sci Shenyang Inst Automat State Key Lab Robot Shenyang 110016 Peoples R China Chinese Acad Sci Inst Robot & Intelligent Mfg Shenyang 110016 Peoples R China Univ Chinese Acad Sci Huairou 100049 Peoples R China 

出 版 物：《IEEE SIGNAL PROCESSING LETTERS》 (IEEE信号处理快报)

年 卷 期：2020年第27卷第0期

页      面：316-320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 [91648118, 61991413, 61821005] LiaoNing Revitalization Talents Program 

主　　题：Image deraining pixel-wise attention encoder-decoder skip connection 

摘      要：Recent single image deraining methods either use a recurrent mechanism to gradually learn the mapping between clear images and rainy images, or focus on designing various loss functions to supervise the learning process. In this letter, we propose a dually connected deraining net using pixel-wise attention, for single image rain removal. Specifically, the deraining net adopts an encoder-decoder net as a backbone, which can effectively learn a residual rain-streaks map by jointly using skip sum connection and skip concatenation connection. The dual connections enable the deraining net to promote information flow between layers, and thus can allow it to discriminate and localize the rain streaks. To preserve image details, the decoded features are weighted by the learnable pixel-wise attention for adaptively recalibrating their responses. Experimental results on synthetic datasets demonstrate that the proposed model outperforms the recent state-of-the-art deraining methods.