Contrastive Learning for Blind Super-Resolution via A Distortion-Specific Network

doi:10.1109/JAS.2022.105914

CASIA OpenIR > 学术期刊 > IEEE/CAA Journal of Automatica Sinica

	Contrastive Learning for Blind Super-Resolution via A Distortion-Specific Network
	Xinya Wang; Jiayi Ma; Junjun Jiang
发表期刊	IEEE/CAA Journal of Automatica Sinica
ISSN	2329-9266
	2023
卷号	10 期号:1 页码:78-89
摘要	Previous deep learning-based super-resolution (SR) methods rely on the assumption that the degradation process is predefined (e.g., bicubic downsampling). Thus, their performance would suffer from deterioration if the real degradation is not consistent with the assumption. To deal with real-world scenarios, existing blind SR methods are committed to estimating both the degradation and the super-resolved image with an extra loss or iterative scheme. However, degradation estimation that requires more computation would result in limited SR performance due to the accumulated estimation errors. In this paper, we propose a contrastive regularization built upon contrastive learning to exploit both the information of blurry images and clear images as negative and positive samples, respectively. Contrastive regularization ensures that the restored image is pulled closer to the clear image and pushed far away from the blurry image in the representation space. Furthermore, instead of estimating the degradation, we extract global statistical prior information to capture the character of the distortion. Considering the coupling between the degradation and the low-resolution image, we embed the global prior into the distortion-specific SR network to make our method adaptive to the changes of distortions. We term our distortion-specific network with contrastive regularization as CRDNet. The extensive experiments on synthetic and real-world scenes demonstrate that our lightweight CRDNet surpasses state-of-the-art blind super-resolution approaches.
关键词	Blind super-resolution contrastive learning deep learning image super-resolution (SR)
DOI	10.1109/JAS.2022.105914
引用统计	被引频次：7[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/173211/50728
专题	学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式 GB/T 7714	Xinya Wang,Jiayi Ma,Junjun Jiang. Contrastive Learning for Blind Super-Resolution via A Distortion-Specific Network[J]. IEEE/CAA Journal of Automatica Sinica,2023,10(1):78-89.
APA	Xinya Wang,Jiayi Ma,&Junjun Jiang.(2023).Contrastive Learning for Blind Super-Resolution via A Distortion-Specific Network.IEEE/CAA Journal of Automatica Sinica,10(1),78-89.
MLA	Xinya Wang,et al."Contrastive Learning for Blind Super-Resolution via A Distortion-Specific Network".IEEE/CAA Journal of Automatica Sinica 10.1(2023):78-89.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
JAS-2022-0497.pdf（11082KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载