文献类型：期刊文献

英文题名：AFF-Dehazing: Attention-based feature fusion network for low-light image Dehazing

作者：Zhou, Yu[1];Chen, Zhihua[1];Sheng, Bin[2];Li, Ping[3];Kim, Jinman[4];Wu, Enhua[5,6]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai, Peoples R China;[2]Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Shanghai, Peoples R China;[3]Hong Kong Polytech Univ, Dept Comp, Kowloon, Hong Kong, Peoples R China;[4]Univ Sydney, Sch Informat Technol, Sydney, NSW, Australia;[5]Chinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing, Peoples R China;[6]Univ Macau, Fac Sci & Technol, Macau, Peoples R China

年份：2021

卷号：32

期号：3-4

外文期刊名：COMPUTER ANIMATION AND VIRTUAL WORLDS

收录：;EI(收录号：20212110409436);WOS:【SCI-EXPANDED(收录号:WOS:000653157800001)】；

基金：Hong Kong Polytechnic University, Grant/Award Numbers: P0030419, P0030929, P0035358; National Natural Science Foundation of China, Grant/Award Numbers: 61572316, 61632003, 61672228, 61872241, 61902126, 62072449

语种：英文

外文关键词：attention mechanism; image dehazing; low-light enhancement

摘要：Images captured in haze conditions, especially at nighttime with low light, often suffer from degraded visibility, contrasts, and vividness, which makes it difficult to carry out the following vision tasks. In this article, we propose an attention-based feature fusion network (AFF-Dehazing) for low-light image dehazing. Our method decomposes the low-light image dehazing into two task-independent streams containing four modules: image dehazing module, low-light feature extractor module, feature fusion module, and image restoration module. The basic block of these modules is the proposed attention-based residual dense block. Since the dual-branch are used, AFF-Dehazing can avoid learning the mixed degradation all-in-one and enhance the details of low-light haze images. Extensive experiments show that our method surpasses previous state-of-the-art image dehazing methods and low-light enhancement methods by a very large margin both quantitatively and qualitatively.