A Review of Single Image Super-resolution Based on Deep Learning

doi:10.16383/j.aas.c190031

CIOMP OpenIR

	A Review of Single Image Super-resolution Based on Deep Learning
	N. Zhang,W. Y.-C,Z. X and X. D.-D
	2020
发表期刊	Zidonghua Xuebao/Acta Automatica Sinica
ISSN	2544156
卷号	46 期号:12 页码:2479-2499
摘要	Super-resolution (SR) refers to an estimation of high resolution (HR) image from one or more low resolution (LR) observations of the same scene, usually employing digital image processing and machine learning techniques. This technique can effectively improve image resolution without upgrading hardware devices. In recent years, deep learning has developed rapidly in the image field, and it has brought promising prospects for single-image super-resolution (SISR). This paper summarizes the research status and development tendency of the current SISR methods based on deep learning. First, we introduce a series of networks characteristics for SISR, and analysis of these networks in the structure, input, loss function, scale factors and evaluation criterion are given. Then according to the experimental results, we discuss the existing problems and solutions. Finally, the future development and challenges of the SISR methods based on deep learning are presented. Copyright 2020 Acta Automatica Sinica. All rights reserved.
DOI	10.16383/j.aas.c190031
URL	查看原文
收录类别	EI
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/64863
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	N. Zhang,W. Y.-C,Z. X and X. D.-D. A Review of Single Image Super-resolution Based on Deep Learning[J]. Zidonghua Xuebao/Acta Automatica Sinica,2020,46(12):2479-2499.
APA	N. Zhang,W. Y.-C,Z. X and X. D.-D.(2020).A Review of Single Image Super-resolution Based on Deep Learning.Zidonghua Xuebao/Acta Automatica Sinica,46(12),2479-2499.
MLA	N. Zhang,W. Y.-C,Z. X and X. D.-D."A Review of Single Image Super-resolution Based on Deep Learning".Zidonghua Xuebao/Acta Automatica Sinica 46.12(2020):2479-2499.

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
A Review of Single I（2246KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览请求全文