文献类型：期刊文献

英文题名：SCPA-Net: Self-calibrated pyramid aggregation for image dehazing

作者：Chen, Zhihua[1];Zhou, Yu[1];Li, Ran[1];Li, Ping[2,3];Sheng, Bin[4]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai, Peoples R China;[2]Hong Kong Polytech Univ, Dept Comp, Hong Kong, Peoples R China;[3]Hong Kong Polytech Univ, Sch Design, Hung Hom, Hong Kong, Peoples R China;[4]Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Shanghai, Peoples R China

年份：2022

卷号：33

期号：3-4

外文期刊名：COMPUTER ANIMATION AND VIRTUAL WORLDS

收录：;EI(收录号：20222312190569);WOS:【SCI-EXPANDED(收录号:WOS:000805154000001)】；

基金：National Natural Science Foundation of China, Grant/Award Numbers: 61572316, 61872241; Shanghai Municipal Science and Technology Major Project, Grant/Award Number: 2021SHZDZX0102; Hong Kong Polytechnic University, Grant/Award Numbers: P0030419, P0030929, P0035358

语种：英文

外文关键词：image dehazing; pyramid upsampling structure; self-attention; self-calibration

摘要：Dehazing as an important image processing field has developed for many years, there exist many excellent methods for exploring more complex networks to solve this problem. In this paper, instead of designing a complex network structure, we propose a novel dehazing network based on the consideration of enhancing feature aggregation and feature representation abilities of dehazing architecture. Specifically, we propose a self-calibrated pyramid aggregation network (SCPA-Net) for image dehazing, which is based on an encoder-decoder architecture. In the encoder, we build a self-attention block as a unit to aggregate information from a neighborhood to adapt to its content. In the decoder, we introduce a self-calibration block to capture long-range spatial and channel dependencies to produce more discriminative representations. Finally, to learn the scale information, the pyramid upsampling structure is applied to aggregate the multiscale self-calibrated attentive features. Experimental results show our SCPA-Net can achieve impressive dehazing performance.