Underwater Image Enhancement via Physical-Feedback Adversarial Transfer Learning

doi:10.1109/JOE.2021.3104055

IOCAS-IR

	Underwater Image Enhancement via Physical-Feedback Adversarial Transfer Learning
	Zhou, Yuan 1; Yan, Kangming 2; Li, Xiaofeng 3
	2021-09-23
发表期刊	IEEE JOURNAL OF OCEANIC ENGINEERING
ISSN	0364-9059
页码	12
通讯作者	Li, Xiaofeng([email protected])
摘要	This article proposes a domain adaptive learning framework based on physical model feedback for underwater image enhancement. Underwater image enhancement involves mapping from low-quality underwater images to their dewatered counterparts. Due to the lack of dewatered images as ground truth, most learning-based methods are trained using synthetic datasets. However, they usually ignored the domain gap between synthetic training data and real-world testing data, which seriously reduces the generalization ability of those models when testing on real underwater images. We solve the problem by embedding a domain adaptive mechanism in a learning framework to eliminate the domain gap. However, the basic formulation of a domain adaptive-based learning framework does not generate realistic images in color and details. Motivated by an observation that the estimated results should be consistent with the physical model of underwater imaging, we propose a physics constraint as a feedback controller so that it can guide the estimation of underwater image enhancement. Extensive experiments validate the superiority of the proposed framework.
关键词	Degradation Adaptation models Image restoration Image color analysis Image enhancement Convolutional neural networks Data models Degradation model domain adaptation generative adversarial networks underwater image enhancement
DOI	10.1109/JOE.2021.3104055
收录类别	SCI
语种	英语
资助项目	Strategic Priority Research Program of the Chinese Academy of Sciences (CAS)[XDA19060101]; Key R&D project of Shandong Province[2019JZZY010102]; National Natural Science Foundation of China-Shandong Science Foundation[U2006211]; Key deployment project of Center for Ocean Mega-Science, CAS[COMS2019R02]; CAS[Y9KY04101L]
WOS研究方向	Engineering ; Oceanography
WOS类目	Engineering, Civil ; Engineering, Ocean ; Engineering, Electrical & Electronic ; Oceanography
WOS记录号	WOS:000732190800001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：28[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.qdio.ac.cn/handle/337002/177534
专题	中国科学院海洋研究所
通讯作者	Li, Xiaofeng
作者单位	1.Tianjin Univ, Sch Elect & Informat Engn, Tianjin 300072, Peoples R China 2.Tianjin Univ, Tianjin Int Engn Inst, Tianjin 300072, Peoples R China 3.Chinese Acad Sci, Inst Oceanol, Qingdao 266071, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Yuan,Yan, Kangming,Li, Xiaofeng. Underwater Image Enhancement via Physical-Feedback Adversarial Transfer Learning[J]. IEEE JOURNAL OF OCEANIC ENGINEERING,2021:12.
APA	Zhou, Yuan,Yan, Kangming,&Li, Xiaofeng.(2021).Underwater Image Enhancement via Physical-Feedback Adversarial Transfer Learning.IEEE JOURNAL OF OCEANIC ENGINEERING,12.
MLA	Zhou, Yuan,et al."Underwater Image Enhancement via Physical-Feedback Adversarial Transfer Learning".IEEE JOURNAL OF OCEANIC ENGINEERING (2021):12.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Underwater_Image_Enh（8751KB）	期刊论文	出版稿	限制开放	CC BY-NC-SA	浏览