文献类型：期刊文献

英文题名：M-CBN: Manifold constrained joint image dehazing and super-resolution based on chord boosting network

作者：Wang, Pengyu[1];Zhu, Hongqing[1];Zhang, Han[1];Wang, Nan[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China

年份：2023

卷号：135

外文期刊名：PATTERN RECOGNITION

收录：;EI(收录号：20224713140568);WOS:【SCI-EXPANDED(收录号:WOS:000891815700001)】；

基金：The authors would like to thank the anonymous reviewers and the associate editor for their insightful comments that signifi- cantly improved the quality of this paper. This work was supported by the National Nature Science Foundation of China under Grant 61872143 .

语种：英文

外文关键词：Image dehazing; Chord boosting network; Super -resolution; Frequency feature cross -collaboration; Manifold constraint

摘要：This paper proposes a Manifold Constrained Chord Boosting Network (M-CBN), which incorporates the super-resolution principle to achieve image dehazing. M-CBN is a task-specific image restoration network that explicitly learns the mapping from Low-resolution (LR) hazy images to High-resolution (HR) haze -free images. Hence, we design a preliminary image degradation to imitate super-resolution training on hazy images. In M-CBN, a plug-and-play Cross-linked Dual Projection Module (CDPM) for skip connec-tions is developed. In CDPM, back-projections for HR encoder features and LR decoder features are cross -linked for better recovery of spatial information, and a cross-resolution spatial attention is designed to enhance fusion features. Then, to boost the generation of image details and textures, we propose a Chord Residual Module (CRM), which can separately process High-frequency (HF) and Low-frequency (LF) fea-tures by progressive inner-frequency updating and dense inter-frequency cross-collaboration to enhance decoding features. Finally, a manifold constraint dual discriminator is established. The static discriminator explicitly constrains dehazed images in the expected manifold to unify the joint learning of image dehaz-ing and super-resolution. And the dynamic discriminator implicitly optimizes the network by adversarial training. Extensive experiments on general, dense and non-homogeneous haze datasets and cross-domain dehazing tasks show the proposed M-CBN presents high-quality dehazed results with natural colors and clear details.(c) 2022 Elsevier Ltd. All rights reserved.