文献类型：期刊文献

英文题名：Frequency-oriented hierarchical fusion network for single image raindrop removal

作者：Wang, Juncheng[1] Zhang, Jie[1] Guo, Shuai[2] Li, Bo[3]

第一作者：Wang, Juncheng

通信作者：Wang, JC[1]

机构：[1]Qingdao Univ Technol, Sch Humanities & Foreign Languages, Qingdao, Peoples R China;[2]Qingdao Univ Technol, Sch Sci, Qingdao, Peoples R China;[3]Chinese Acad Forestry, Res Inst Forestry Policy & Informat, Beijing, Peoples R China

年份：2024

卷号：19

期号：5

外文期刊名：PLOS ONE

收录：;Scopus(收录号：2-s2.0-85194126453);WOS:【SCI-EXPANDED(收录号:WOS:001231237700010)】；

基金：This work was supported by Youth Program of Natural Science Foundation of Shandong Province (ZR2020QF028). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. The author receives no salary from the funder.

语种：英文

摘要：Single image raindrop removal aims at recovering high-resolution images from degraded ones. However, existing methods primarily employ pixel-level supervision between image pairs to learn spatial features, thus ignoring the more discriminative frequency information. This drawback results in the loss of high-frequency structures and the generation of diverse artifacts in the restored image. To ameliorate this deficiency, we propose a novel frequency-oriented Hierarchical Fusion Network (HFNet) for raindrop image restoration. Specifically, to compensate for spatial representation deficiencies, we design a dynamic adaptive frequency loss (DAFL), which allows the model to adaptively handle the high-frequency components that are difficult to recover. To handle spatially diverse raindrops, we propose a hierarchical fusion network to efficiently learn both contextual information and spatial features. Meanwhile, a calibrated attention mechanism is proposed to facilitate the transfer of valuable information. Comparative experiments with existing methods indicate the advantages of the proposed algorithm.