中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 中科院工业视觉智能装备工程实验室
  5. 精密感知与控制
SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement With Multi-Scale Perception

文献类型：期刊论文

作者Qi, Qi6; Li, Kunqian5; Zheng, Haiyong4; Gao, Xiang3,5; Hou, Guojia2; Sun, Kun1
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2022
卷号31页码:6816-6830
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
ISSN号1057-7149
DOI10.1109/TIP.2022.3216208
通讯作者Li, Kunqian(likunqian@ouc.edu.cn)
英文摘要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.
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]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000875886800010
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China ; Natural Science Foundation of Shandong Province ; Fundamental Research Funds for the Central Universities
源URL[http://ir.ia.ac.cn/handle/173211/50556]  
专题精密感知与控制研究中心_精密感知与控制
通讯作者Li, Kunqian
作者单位1.China Univ Geosci, Sch Comp Sci, Wuhan 430078, Peoples R China
2.Qingdao Univ, Coll Comp Sci & Technol, Qingdao 266071, Peoples R China
3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
4.Ocean Univ China, Coll Elect Engn, Intelligent Informat Sensing & Proc Lab, Qingdao 266100, Peoples R China
5.Ocean Univ China, Coll Engn, Qingdao 266100, Peoples R China
6.Ocean Univ China, Fac Informat Sci & Engn, Qingdao 266100, 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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。