Video super-resolution based on spatial-temporal recurrent residual networks

doi:10.1016/j.cviu.2017.09.002

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Video super-resolution based on spatial-temporal recurrent residual networks
	Yang, Wenhan 1; Feng, Jiashi 2; Xie, Guosen3 ; Liu, Jiaying 1; Guo, Zongming 1; Yan, Shuicheng 4
发表期刊	COMPUTER VISION AND IMAGE UNDERSTANDING
	2018-03-01
卷号	168 页码:79-92
文章类型	Article
摘要	In this paper, we propose a new video Super-Resolution (SR) method by jointly modeling intra-frame redundancy and inter-frame motion context in a unified deep network. Different from conventional methods, the proposed Spatial-Temporal Recurrent Residual Network (STR-ResNet) investigates both spatial and temporal residues, which are represented by the difference between a high resolution (HR) frame and its corresponding low resolution (LR) frame and the difference between adjacent HR frames, respectively. This spatial-temporal residual learning model is then utilized to connect the intra-frame and inter-frame redundancies within video sequences in a recurrent convolutional network and to predict HR temporal residues in the penultimate layer as guidance to benefit estimating the spatial residue for video SR. Extensive experiments have demonstrated that the proposed STR-ResNet is able to efficiently reconstruct videos with diversified contents and complex motions, which outperforms the existing video SR approaches and offers new state-of-the-art performances on benchmark datasets.
关键词	Spatial Residue Temporal Residue Video Super-resolution Inter-frame Motion Context Intra-frame Redundancy
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.cviu.2017.09.002
关键词[WOS]	IMAGE SUPERRESOLUTION ; SUPER RESOLUTION ; REGULARIZATION ; ALGORITHM
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61772043) ; State Scholarship Fund from the China Scholarship Council
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000429185700007
引用统计	被引频次：41[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/173211/21997
专题	多模态人工智能系统全国重点实验室_模式分析与学习
作者单位	1.Peking Univ, Inst Comp Sci & Technol, Beijing 100871, Peoples R China 2.Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 117583, Singapore 3.Chinese Acad Sci, Inst Automat, NLPR, Beijing 100190, Peoples R China 4.Qihoo 360 Technol Co Ltd, Artificial Intelligence Inst, Beijing 100015, Peoples R China
推荐引用方式 GB/T 7714	Yang, Wenhan,Feng, Jiashi,Xie, Guosen,et al. Video super-resolution based on spatial-temporal recurrent residual networks[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2018,168:79-92.
APA	Yang, Wenhan,Feng, Jiashi,Xie, Guosen,Liu, Jiaying,Guo, Zongming,&Yan, Shuicheng.(2018).Video super-resolution based on spatial-temporal recurrent residual networks.COMPUTER VISION AND IMAGE UNDERSTANDING,168,79-92.
MLA	Yang, Wenhan,et al."Video super-resolution based on spatial-temporal recurrent residual networks".COMPUTER VISION AND IMAGE UNDERSTANDING 168(2018):79-92.