Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhao, Chen, Cai, Weiling, Dong, Chenyu, Zeng, Ziqi
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2309.04089
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909077906391040
author Zhao, Chen
Cai, Weiling
Dong, Chenyu
Zeng, Ziqi
author_facet Zhao, Chen
Cai, Weiling
Dong, Chenyu
Zeng, Ziqi
contents Underwater images suffer from complex and diverse degradation, which inevitably affects the performance of underwater visual tasks. However, most existing learning-based Underwater image enhancement (UIE) methods mainly restore such degradations in the spatial domain, and rarely pay attention to the fourier frequency information. In this paper, we develop a novel UIE framework based on spatial-frequency interaction and gradient maps, namely SFGNet, which consists of two stages. Specifically, in the first stage, we propose a dense spatial-frequency fusion network (DSFFNet), mainly including our designed dense fourier fusion block and dense spatial fusion block, achieving sufficient spatial-frequency interaction by cross connections between these two blocks. In the second stage, we propose a gradient-aware corrector (GAC) to further enhance perceptual details and geometric structures of images by gradient map. Experimental results on two real-world underwater image datasets show that our approach can successfully enhance underwater images, and achieves competitive performance in visual quality improvement. The code is available at https://github.com/zhihefang/SFGNet.
format Preprint
id arxiv_https___arxiv_org_abs_2309_04089
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Toward Sufficient Spatial-Frequency Interaction for Gradient-aware Underwater Image Enhancement
Zhao, Chen
Cai, Weiling
Dong, Chenyu
Zeng, Ziqi
Computer Vision and Pattern Recognition
Underwater images suffer from complex and diverse degradation, which inevitably affects the performance of underwater visual tasks. However, most existing learning-based Underwater image enhancement (UIE) methods mainly restore such degradations in the spatial domain, and rarely pay attention to the fourier frequency information. In this paper, we develop a novel UIE framework based on spatial-frequency interaction and gradient maps, namely SFGNet, which consists of two stages. Specifically, in the first stage, we propose a dense spatial-frequency fusion network (DSFFNet), mainly including our designed dense fourier fusion block and dense spatial fusion block, achieving sufficient spatial-frequency interaction by cross connections between these two blocks. In the second stage, we propose a gradient-aware corrector (GAC) to further enhance perceptual details and geometric structures of images by gradient map. Experimental results on two real-world underwater image datasets show that our approach can successfully enhance underwater images, and achieves competitive performance in visual quality improvement. The code is available at https://github.com/zhihefang/SFGNet.
title Toward Sufficient Spatial-Frequency Interaction for Gradient-aware Underwater Image Enhancement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.04089