Degradation regression with uncertainty for blind super-resolution

doi:10.1016/j.neucom.2024.127486

CASIA OpenIR > 数字内容技术与服务研究中心 > 版权智能与文化计算

	Degradation regression with uncertainty for blind super-resolution
	Li, Shang1,3 ; Zhang, Guixuan2,3 ; Luo, Zhengxiong1,3 ; Liu, Jie2,3 ; Zeng, Zhi2 ; Zhang, Shuwu2,3
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
	2024-05-14
卷号	582 页码:14
通讯作者	Zeng, Zhi(zhi.zeng@bupt.edu.cn)
摘要	Some recent blind super -resolution (SR) efforts focus on designing complex degradation models to better simulate real -world degradations. The paired high -resolution (HR) & low -resolution (LR) samples synthesized by these models can cover a large degradation space, which helps train a robust SR model in real scenarios. However, these diverse synthetic samples may render the SR model degradation -unaware and prevent it from achieving optimal results on LR images with specific degradations. Alternatively, another category of methods is proposed to estimate specific degradations in the given application and then tailor a degradation -aware SR model accordingly. Nonetheless, degradation estimation is an ill -posed problem and accurate estimation is quite challenging. Towards these issues, we propose a probabilistic degradation estimator (PDE) which can predict the degradation as a certain distribution rather than a single point. Specifically, we develop an intersection over union (IoU) based degradation regression loss with uncertainty, which could lead PDE to shrink the possible degradation space of the test LR image. This enables the degradation model to synthesize more degradationspecific training samples and further improve SR performance. In this way, our PDE can alleviate degradation redundancy compared with degradation -unaware methods and is more robust to the degradation estimation error than previous degradation -aware methods. Extensive experiments show that the proposed PDE can help the SR model produce better results on both synthetic and real -world images.
关键词	Blind super-resolution Degradation estimation Uncertainty learning
DOI	10.1016/j.neucom.2024.127486
关键词[WOS]	IMAGE QUALITY ASSESSMENT ; NETWORK
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2022YFF0902202]
项目资助者	National Key R&D Program of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001221617100001
出版者	ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58398
专题	数字内容技术与服务研究中心_版权智能与文化计算
通讯作者	Zeng, Zhi
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 2.Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Beijing 100876, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Li, Shang,Zhang, Guixuan,Luo, Zhengxiong,et al. Degradation regression with uncertainty for blind super-resolution[J]. NEUROCOMPUTING,2024,582:14.
APA	Li, Shang,Zhang, Guixuan,Luo, Zhengxiong,Liu, Jie,Zeng, Zhi,&Zhang, Shuwu.(2024).Degradation regression with uncertainty for blind super-resolution.NEUROCOMPUTING,582,14.
MLA	Li, Shang,et al."Degradation regression with uncertainty for blind super-resolution".NEUROCOMPUTING 582(2024):14.