Single Image Super-Resolution With Multiscale Similarity Learning

doi:10.1109/TNNLS.2013.2262001

OPT OpenIR > 光谱成像技术研究室

	Single Image Super-Resolution With Multiscale Similarity Learning
	Zhang, Kaibing 1; Gao, Xinbo 2; Tao, Dacheng3,4 ; Li, Xuelong5
	2013-10-01
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷号	24 期号:10 页码:1648-1659
摘要	Example learning-based image super-resolution (SR) is recognized as an effective way to produce a high-resolution (HR) image with the help of an external training set. The effectiveness of learning-based SR methods, however, depends highly upon the consistency between the supporting training set and low-resolution (LR) images to be handled. To reduce the adverse effect brought by incompatible high-frequency details in the training set, we propose a single image SR approach by learning multiscale self-similarities from an LR image itself. The proposed SR approach is based upon an observation that small patches in natural images tend to redundantly repeat themselves many times both within the same scale and across different scales. To synthesize the missing details, we establish the HR-LR patch pairs using the initial LR input and its down-sampled version to capture the similarities across different scales and utilize the neighbor embedding algorithm to estimate the relationship between the LR and HR image pairs. To fully exploit the similarities across various scales inside the input LR image, we accumulate the previous resultant images as training examples for the subsequent reconstruction processes and adopt a gradual magnification scheme to upscale the LR input to the desired size step by step. In addition, to preserve sharper edges and suppress aliasing artifacts, we further apply the nonlocal means method to learn the similarity within the same scale and formulate a nonlocal prior regularization term to well pose SR estimation under a reconstruction-based SR framework. Experimental results demonstrate that the proposed method can produce compelling SR recovery both quantitatively and perceptually in comparison with other state-of-the-art baselines.
文章类型	Article
关键词	Image Super-resolution (Sr) Multiscale Self-similarities Neighbor Embedding (Ne) Nonlocal Means (Nlm)
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TNNLS.2013.2262001
收录类别	SCI ; EI
关键词[WOS]	QUALITY ASSESSMENT ; KERNEL REGRESSION ; NONLOCAL-MEANS ; INTERPOLATION ; ALGORITHM ; REGULARIZATION ; RESTORATION
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000325981400012
引用统计	被引频次：118[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/23479
专题	光谱成像技术研究室
作者单位	1.Hubei Engn Univ, Sch Comp & Informat Sci, Xiaogan 432000, Peoples R China 2.Xidian Univ, Sch Elect Engn, Xian 710071, Peoples R China 3.Univ Technol Sydney, Ctr Quantum Computat & Intelligent Syst, Ultimo, NSW 2007, Australia 4.Univ Technol Sydney, Fac Engn & Informat Technol, Ultimo, NSW 2007, Australia 5.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr Opt Imagery Anal & Learning, State Key Lab Transient Opt & Photon, Xian 710119, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Kaibing,Gao, Xinbo,Tao, Dacheng,et al. Single Image Super-Resolution With Multiscale Similarity Learning[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2013,24(10):1648-1659.
APA	Zhang, Kaibing,Gao, Xinbo,Tao, Dacheng,&Li, Xuelong.(2013).Single Image Super-Resolution With Multiscale Similarity Learning.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,24(10),1648-1659.
MLA	Zhang, Kaibing,et al."Single Image Super-Resolution With Multiscale Similarity Learning".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 24.10(2013):1648-1659.

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
Single Image Super-R（1949KB）	期刊论文	出版稿	限制开放	CC BY	请求全文