Video super-resolution with inverse recurrent net and hybrid local fusion

doi:10.1016/j.neucom.2022.03.019

HFCAS OpenIR

	Video super-resolution with inverse recurrent net and hybrid local fusion
	Li, Dingyi 1,2; Wang, Zengfu3,4 ; Yang, Jian 1,2
	2022-06-07
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
通讯作者	Li, Dingyi(lidingyi@njust.edu.cn)
摘要	Video super-resolution converts low-resolution videos to sharp high-resolution ones. In order to make better use of temporal information in video super-resolution, we design inverse recurrent net and hybrid local fusion. We concatenate the original low-resolution input sequence and its inverse sequence repeatedly. The new sequence is viewed as a combination of different stages, and is processed sequentially by using orent net. The outputs of the last two stages in opposite directions are fused to generate the final images. Our inverse recurrent net can extract more bidirectional temporal information in the input sequence, without adding parameter to the corresponding unidirectional recurrent net. We also propose a hybrid local fusion method which uses parallel fusion and cascade fusion for incorporating slidingwindow-based methods into our inverse recurrent net. Extensive experimental results demonstrate the effectiveness of the proposed inverse recurrent net and hybrid local fusion, in terms of visual quality and quantitative evaluations. The code will be released at https://github.com/5ofwind. (c) 2022 Elsevier B.V. All rights reserved.
关键词	Video super-resolution Bidirectional recurrent convolutional neural network Sliding-window Local fusion
DOI	10.1016/j.neucom.2022.03.019
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62002168]
项目资助者	National Natural Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000782510100004
出版者	ELSEVIER
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.hfcas.ac.cn:8080/handle/334002/128596
专题	中国科学院合肥物质科学研究院
通讯作者	Li, Dingyi
作者单位	1.Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, PCA Lab,Minist Educ, Key Lab Intelligent Percept & Syst High Dimens In, Nanjing 210094, Jiangsu, Peoples R China 2.Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Jiangsu Key Lab Image & Video Understanding Socia, Nanjing 210094, Jiangsu, Peoples R China 3.Chinese Acad Sci, Inst Intelligent Machines, Hefei 230031, Anhui, Peoples R China 4.Univ Sci & Technol China, Dept Automation, Hefei 230027, Anhui, Peoples R China
推荐引用方式 GB/T 7714	Li, Dingyi,Wang, Zengfu,Yang, Jian. Video super-resolution with inverse recurrent net and hybrid local fusion[J]. NEUROCOMPUTING,2022,489.
APA	Li, Dingyi,Wang, Zengfu,&Yang, Jian.(2022).Video super-resolution with inverse recurrent net and hybrid local fusion.NEUROCOMPUTING,489.
MLA	Li, Dingyi,et al."Video super-resolution with inverse recurrent net and hybrid local fusion".NEUROCOMPUTING 489(2022).