文献类型：期刊文献

英文题名：DPAFD-net: A dual-path adaptive fusion dehazing network

作者：Zhang, Chenyang[3];Jing, Hongyuan[1,3,4];Wei, Shuang[3];Chen, Jiaxing[3];Shang, Xinna[2,3];Chen, Aidong[2,3]

通讯作者：Jing, HY[1]

机构：[1]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, 97 Beisihuan East Rd, Beijing 100101, Peoples R China;[2]Beijing Union Univ, Multiagent Syst Res Ctr, 97 Beisihuan East Rd, Beijing 100101, Peoples R China;[3]Beijing Union Univ, Coll Robot, 4 Gongti North Rd, Beijing, Peoples R China;[4]Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China

第一机构：北京联合大学北京市信息服务工程重点实验室

通讯机构：[1]corresponding author), Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China.|[1141739]北京联合大学机器人学院;[11417]北京联合大学;

年份：2024

卷号：98

外文期刊名：JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION

收录：;EI(收录号：20235115259070);Scopus(收录号：2-s2.0-85180004220);WOS:【SCI-EXPANDED(收录号:WOS:001139021700001)】；

基金：1 These authors contributed equally to this work. This work is mainly supported by the Beijing Municipal Education Commission Research Foundation under Grant KM202111417008; Sponsored by Beiing NovaProgram under Grant 20230484477 supported by National key research and development plan under Grant 2022YFB2804402; which is also supported by the Academic Research Projects of Beijing Union University No. ZK90202104, No. ZKZD202301, No. JK202309, and partly support by Beijing Union University students' science and technology innovation project No. 20232020.

语种：英文

外文关键词：Image dehazing; Dual-path network; Adaptive fusion; Scale-invariant subnetwork; Structure extraction subnetwork

摘要：Image dehazing is an ill-posed problem that has been extensively studied in recent years. Unfortunately, most existing deep dehazing models have high computational complexity and lack the dynamic adjustment of details, which hinders their application to high-resolution images in computational vision tasks. In this paper, we propose an efficient dual-path adaptive fusion dehazing network (DPAFD-Net) to directly restore a clear image from a hazy input. Moreover, we propose a pure subnetwork with encoder and decoder structures to further extract the structural information and progressively restore the haze-free image. To evaluate the effectiveness of the proposed method, we validate our approach on synthetic and real hazy images, where our method performs favourably against the state-of-the-art dehazing approaches.