A review of deep-learning-based super-resolution: From methods to applications

doi:10.1016/j.patcog.2024.110935

	A review of deep-learning-based super-resolution: From methods to applications
	Su, Hu1,2 ; Li, Ying 1; Xu, Yifan2 ; Fu, Xiang2 ; Liu, Song2,3
	2025-01
发表期刊	PATTERN RECOGNITION (IF:7.5[JCR-2023],7.6[5-Year])
ISSN	0031-3203
EISSN	1873-5142
卷号	157
发表状态	已发表
DOI	10.1016/j.patcog.2024.110935
摘要	Super-resolution (SR), aiming to super-resolve degraded low-resolution image to recover the corresponding high-resolution counterpart, is an important and challenging task in computer vision, and with various applications. The emergence of deep learning (DL) has significantly advanced SR methods, surpassing the performance of traditional techniques. This paper presents a comprehensive survey of DL-based SR methods encompassing single image super resolution (SISR) and multiple image super resolution (MISR) methods, along with their applications and limitations. In SISR methods, addressing individual images independently, we review blind and non-blind SR methods. Additionally, within MISR, we delve into multi-frame, multi-view, and reference-based SR methods. DL-based SR methods are categorized from the application perspective and a taxonomy is proposed. Finally, we present research prospects and future directions. © 2024
关键词	Deep learning Degradation model Image super resolutions Multiple image Multiple image super-resolution Single image super-resolution Single images Superresolution Superresolution methods
URL	查看原文
收录类别	SCI ; EI
语种	英语
资助项目	National Key Research and Development Program of China[2021ZD0114505] ; National Natural Science Foundation of China[62303321]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001302255600001
出版者	Elsevier Ltd
EI入藏号	20243516943362
EI主题词	Deep learning
EI分类号	1101.2.1
原始文献类型	Journal article (JA)
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/415586
专题	信息科学与技术学院信息科学与技术学院_本科生信息科学与技术学院_博士生信息科学与技术学院_PI研究组_刘松组
通讯作者	Liu, Song
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing, Peoples R China 2.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China 3.Shanghai Engn Res Ctr Intelligent Vis & Imaging, Shanghai, Peoples R China
第一作者单位	信息科学与技术学院
通讯作者单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Su, Hu,Li, Ying,Xu, Yifan,et al. A review of deep-learning-based super-resolution: From methods to applications[J]. PATTERN RECOGNITION,2025,157.
APA	Su, Hu,Li, Ying,Xu, Yifan,Fu, Xiang,&Liu, Song.(2025).A review of deep-learning-based super-resolution: From methods to applications.PATTERN RECOGNITION,157.
MLA	Su, Hu,et al."A review of deep-learning-based super-resolution: From methods to applications".PATTERN RECOGNITION 157(2025).