Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution

doi:10.1109/TIP.2023.3240845

	Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution
	Hao Hou 1; Jun Xu 2; Yingkun Hou 3; Xiaotao Hu 4; Benzheng Wei 5; Dinggang Shen6
	2023
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING (IF:10.8[JCR-2023],12.1[5-Year])
ISSN	1057-7149
EISSN	1941-0042
卷号	32 页码:1184-1199
发表状态	已发表
DOI	10.1109/TIP.2023.3240845
摘要	Real-world face super-resolution (SR) is a highly ill-posed image restoration task. The fully-cycled Cycle-GAN architecture is widely employed to achieve promising performance on face SR, but is prone to produce artifacts upon challenging cases in real-world scenarios, since joint participation in the same degradation branch will impact final performance due to huge domain gap between real-world and synthetic LR ones obtained by generators. To better exploit the powerful generative capability of GAN for real-world face SR, in this paper, we establish two independent degradation branches in the forward and backward cycle-consistent reconstruction processes, respectively, while the two processes share the same restoration branch. Our Semi-Cycled Generative Adversarial Networks (SCGAN) is able to alleviate the adverse effects of the domain gap between the real-world LR face images and the synthetic LR ones, and to achieve accurate and robust face SR performance by the shared restoration branch regularized by both the forward and backward cycle-consistent learning processes. Experiments on two synthetic and two real-world datasets demonstrate that, our SCGAN outperforms the state-of-the-art methods on recovering the face structures/details and quantitative metrics for real-world face SR. The code will be publicly released at https://github.com/HaoHou-98/SCGAN. © 1992-2012 IEEE.
关键词	omputer vision Image reconstruction Network architecture Optical resolving power Restoration Cycle-consistent generative adversarial network Face super-resolution Forward-and-backward Ill posed Joint participation Performance Real-world Real-world face super-resolution Real-world scenario Semi-cycled architecture
URL	查看原文
收录类别	EI ; SCOPUS
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20230813624888
EI主题词	Generative adversarial networks
EI分类号	723.4 Artificial Intelligence ; 723.5 Computer Applications ; 741.1 Light/Optics ; 741.2 Vision
原始文献类型	Journal article (JA)
来源库	IEEE
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/282024
专题	信息科学与技术学院生物医学工程学院生物医学工程学院_PI研究组_沈定刚组
作者单位	1.College of Intelligence and Information Engineering and the Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Jinan, China 2.School of Statistics and Data Science, KLMDASR, LEBPS, and LPMC, Nankai University, Tianjin, China 3.School of Information Science and Technology, Taishan University, Taian, China 4.College of Computer Science, Nankai University, Tianjin, China 5.Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Jinan, China 6.School of Biomedical Engineering, ShanghaiTech University, Shanghai, China
推荐引用方式 GB/T 7714	Hao Hou,Jun Xu,Yingkun Hou,et al. Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2023,32:1184-1199.
APA	Hao Hou,Jun Xu,Yingkun Hou,Xiaotao Hu,Benzheng Wei,&Dinggang Shen.(2023).Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution.IEEE TRANSACTIONS ON IMAGE PROCESSING,32,1184-1199.
MLA	Hao Hou,et al."Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution".IEEE TRANSACTIONS ON IMAGE PROCESSING 32(2023):1184-1199.