Neural texture transfer assisted video coding with adaptive up-sampling

doi:10.1016/j.image.2022.116754

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 三维可视计算

	Neural texture transfer assisted video coding with adaptive up-sampling
	Yu, Li 5,6; Chang, Wenshuai 5,6; Quan, Weize 3,4; Xiao, Jimin 2; Yan, Dong-Ming 3,4; Gabbouj, Moncef 1,6
刊名	SIGNAL PROCESSING-IMAGE COMMUNICATION
	2022-09-01
卷号	107 页码:10
关键词	High-efficiency video coding (HEVC) Reference-based super-resolution Low bitrate Video compression Deep learning Machine learning
ISSN号	0923-5965
DOI	10.1016/j.image.2022.116754
通讯作者	Gabbouj, Moncef(moncef.gabbouj@tuni.fi)
英文摘要	Deep learning techniques have been extensively investigated for the purpose of further increasing the efficiency of traditional video compression. Some deep learning techniques for down/up-sampling-based video coding were found to be especially effective when the bandwidth or storage is limited. Existing works mainly differ in the super-resolution models used. Some works simply use a single image super-resolution model, ignoring the rich information in the correlation between video frames, while others explore the correlation between frames by simply concatenating the features across adjacent frames. This, however, may fail when the textures are not well aligned. In this paper, we propose to utilize neural texture transfer which exploits the semantic correlation between frames and is able to explore the correlated information even when the textures are not aligned. Meanwhile, an adaptive group of pictures (GOP) method is proposed to automatically decide whether a frame should be down-sampled or not. Experimental results show that the proposed method outperforms the standard HEVC and state-of-the-art methods under different compression configurations. When compared to standard HEVC, the BD-rate (PSNR) and BD-rate (SSIM) of the proposed method are up to-19.1% and-26.5%, respectively.
资助项目	National Natural Science Foundation of China[62002172] ; National Natural Science Foundation of China[61972323] ; Natural Science Foundation of the Jiangsu Higher Education Institutions of China[19KJB510040] ; Nanjing Scientific Innovation Foundation for the Returned Overseas Chinese Scholars[R2019LZ04] ; Jiangsu Provincial Double-Innovation Doctor Program[202100002] ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR) , China[2018r080] ; Startup Foundation for Introducing Talent of NUIST, China ; High Performane Computing Center of Nanjing University of Information Science Technology
WOS关键词	LEARNING-BASED SUPERRESOLUTION
WOS研究方向	Engineering
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000812902400002
资助机构	National Natural Science Foundation of China ; Natural Science Foundation of the Jiangsu Higher Education Institutions of China ; Nanjing Scientific Innovation Foundation for the Returned Overseas Chinese Scholars ; Jiangsu Provincial Double-Innovation Doctor Program ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR) , China ; Startup Foundation for Introducing Talent of NUIST, China ; High Performane Computing Center of Nanjing University of Information Science Technology
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/49191]
专题	模式识别国家重点实验室_三维可视计算
通讯作者	Gabbouj, Moncef
作者单位	1.Tampere Univ, Dept Comp Sci, Tampere, Finland 2.Xian Jiaotong Liverpool Univ, Sch Adv Technol, Suzhou 215028, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit NLPR, Beijing 100049, Peoples R China 5.Nanjing Univ Informat Sci & Technol, Engn Res Ctr Digital Forens, Minist Educ, Nanjing 210044, Peoples R China 6.Nanjing Univ Informat Sci & Technol, Sch Comp & Software, Nanjing 210044, Peoples R China
推荐引用方式 GB/T 7714	Yu, Li,Chang, Wenshuai,Quan, Weize,et al. Neural texture transfer assisted video coding with adaptive up-sampling[J]. SIGNAL PROCESSING-IMAGE COMMUNICATION,2022,107:10.
APA	Yu, Li,Chang, Wenshuai,Quan, Weize,Xiao, Jimin,Yan, Dong-Ming,&Gabbouj, Moncef.(2022).Neural texture transfer assisted video coding with adaptive up-sampling.SIGNAL PROCESSING-IMAGE COMMUNICATION,107,10.
MLA	Yu, Li,et al."Neural texture transfer assisted video coding with adaptive up-sampling".SIGNAL PROCESSING-IMAGE COMMUNICATION 107(2022):10.