SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement With Multi-Scale Perception

doi:10.1109/TIP.2022.3216208

CASIA OpenIR > 中科院工业视觉智能装备工程实验室 > 精密感知与控制

	SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement With Multi-Scale Perception
	Qi, Qi 1; Li, Kunqian 2; Zheng, Haiyong 3; Gao, Xiang2,4 ; Hou, Guojia 5; Sun, Kun 6
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
	2022
卷号	31 页码:6816-6830
通讯作者	Li, Kunqian(likunqian@ouc.edu.cn)
摘要	Due to the wavelength-dependent light attenuation, refraction and scattering, underwater images usually suffer from color distortion and blurred details. However, due to the limited number of paired underwater images with undistorted images as reference, training deep enhancement models for diverse degradation types is quite difficult. To boost the performance of data-driven approaches, it is essential to establish more effective learning mechanisms that mine richer supervised information from limited training sample resources. In this paper, we propose a novel underwater image enhancement network, called SGUIE-Net, in which we introduce semantic information as high-level guidance via region-wise enhancement feature learning. Accordingly, we propose semantic region-wise enhancement module to better learn local enhancement features for semantic regions with multi-scale perception. After using them as complementary features and feeding them to the main branch, which extracts the global enhancement features on the original image scale, the fused features bring semantically consistent and visually superior enhancements. Extensive experiments on the publicly available datasets and our proposed dataset demonstrate the impressive performance of SGUIE-Net. The code and proposed dataset are available at https://trentqq.github.io/SGUIE-Net.html.
关键词	Semantics Image enhancement Task analysis Feature extraction Training Degradation Visualization Underwater image enhancement deep learning semantic guidance attention mechanism SUIM-E dataset
DOI	10.1109/TIP.2022.3216208
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61906177] ; National Natural Science Foundation of China[62176242] ; Natural Science Foundation of Shandong Province[ZR2019BF034] ; Fundamental Research Funds for the Central Universities[201964013]
项目资助者	National Natural Science Foundation of China ; Natural Science Foundation of Shandong Province ; Fundamental Research Funds for the Central Universities
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000875886800010
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：33[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/50557
专题	中科院工业视觉智能装备工程实验室_精密感知与控制
通讯作者	Li, Kunqian
作者单位	1.Ocean Univ China, Fac Informat Sci & Engn, Qingdao 266100, Peoples R China 2.Ocean Univ China, Coll Engn, Qingdao 266100, Peoples R China 3.Ocean Univ China, Coll Elect Engn, Intelligent Informat Sensing & Proc Lab, Qingdao 266100, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 5.Qingdao Univ, Coll Comp Sci & Technol, Qingdao 266071, Peoples R China 6.China Univ Geosci, Sch Comp Sci, Wuhan 430078, Peoples R China
推荐引用方式 GB/T 7714	Qi, Qi,Li, Kunqian,Zheng, Haiyong,et al. SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement With Multi-Scale Perception[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2022,31:6816-6830.
APA	Qi, Qi,Li, Kunqian,Zheng, Haiyong,Gao, Xiang,Hou, Guojia,&Sun, Kun.(2022).SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement With Multi-Scale Perception.IEEE TRANSACTIONS ON IMAGE PROCESSING,31,6816-6830.
MLA	Qi, Qi,et al."SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement With Multi-Scale Perception".IEEE TRANSACTIONS ON IMAGE PROCESSING 31(2022):6816-6830.