Joint Learning for Single-Image Super-Resolution via a Coupled Constraint

CORC > 西安光学精密机械研究所 > 中国科学院西安光学精密机械研究所 > 光学影像学习与分析中心

	Joint Learning for Single-Image Super-Resolution via a Coupled Constraint
	Gao, Xinbo 1; Zhang, Kaibing 1; Tao, Dacheng 2; Li, Xuelong 3
刊名	ieee transactions on image processing
	2012-02-01
卷号	21 期号:2 页码:469-480
关键词	Grouping patch pairs (GPPs) joint learning neighbor embedding (NE) super-resolution (SR)
ISSN号	1057-7149
产权排序	4
合作状况	国际
英文摘要	the neighbor-embedding (ne) algorithm for single-image super-resolution (sr) reconstruction assumes that the feature spaces of low-resolution (lr) and high-resolution (hr) patches are locally isometric. however, this is not true for sr because of one-to-many mappings between lr and hr patches. to overcome or at least to reduce the problem for ne-based sr reconstruction, we apply a joint learning technique to train two projection matrices simultaneously and to map the original lr and hr feature spaces onto a unified feature subspace. subsequently, the k-nearest neighbor selection of the input lr image patches is conducted in the unified feature subspace to estimate the reconstruction weights. to handle a large number of samples, joint learning locally exploits a coupled constraint by linking the lr-hr counterparts together with the k-nearest grouping patch pairs. in order to refine further the initial sr estimate, we impose a global reconstruction constraint on the sr outcome based on the maximum a posteriori framework. preliminary experiments suggest that the proposed algorithm outperforms ne-related baselines.
学科主题	computer science ; artificial intelligence ; engineering ; electrical & electronic
WOS标题词	science & technology ; technology
类目[WOS]	computer science, artificial intelligence ; engineering, electrical & electronic
研究领域[WOS]	computer science ; engineering
关键词[WOS]	high-resolution image ; quality assessment ; motion estimation ; super resolution ; interpolation ; reconstruction ; restoration ; recognition ; algorithm ; sequence
收录类别	SCI ; EI
语种	英语
WOS记录号	WOS:000300559700004
公开日期	2012-09-03
内容类型	期刊论文
源URL	[http://ir.opt.ac.cn/handle/181661/20250]
专题	西安光学精密机械研究所_光学影像学习与分析中心
作者单位	1.Xidian Univ, Sch Elect Engn, Xian 710071, Peoples R China 2.Univ Technol Sydney, Fac Engn & Informat Technol, Ctr Quantum Computat & Intelligent Syst, Sydney, NSW 2007, Australia 3.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr OPT IMagery Anal & Learning OPTIMAL, Xian 710119, Peoples R China
推荐引用方式 GB/T 7714	Gao, Xinbo,Zhang, Kaibing,Tao, Dacheng,et al. Joint Learning for Single-Image Super-Resolution via a Coupled Constraint[J]. ieee transactions on image processing,2012,21(2):469-480.
APA	Gao, Xinbo,Zhang, Kaibing,Tao, Dacheng,&Li, Xuelong.(2012).Joint Learning for Single-Image Super-Resolution via a Coupled Constraint.ieee transactions on image processing,21(2),469-480.
MLA	Gao, Xinbo,et al."Joint Learning for Single-Image Super-Resolution via a Coupled Constraint".ieee transactions on image processing 21.2(2012):469-480.