Edge-directed single image super-resolution via cross-resolution sharpening function learning

doi:10.1007/s11042-016-3656-z

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 先进时空数据分析与学习

	Edge-directed single image super-resolution via cross-resolution sharpening function learning
	Han, Wei 1,2; Chu, Jun 1,2; Wang, Lingfeng3 ; Pan, Chunhong3
发表期刊	MULTIMEDIA TOOLS AND APPLICATIONS
	2017-04-01
卷号	76 期号:8 页码:11143-11155
文章类型	Article
摘要	Edge-directed single image super-resolution methods have been paid more attentions due to their sharp edge preserving in the recovered high-resolution image. Their core is the high-resolution gradient estimation. In this paper, we propose a novel cross-resolution gradient sharpening function learning to obtain the high-resolution gradient. The main idea of cross-resolution learning is to learn a sharpening function from low-resolution, and use it in high-resolution. Specifically, a blurred low-resolution image is first constructed by performing bicubic down-sampling and up-sampling operations sequentially. The gradient sharpening function considered as a linear transform is learned from blurred low-resolution gradient to the input low-resolution image gradient. After that, the high-resolution gradient is estimated by applying the learned gradient sharpening function to the initial blurred gradient obtained from the bicubic up-sampled of the low-resolution image. Finally, edge-directed single image super-resolution reconstruction is performed to obtain the sharpened high-resolution image. Extensive experiments demonstrate the effectiveness of our method in comparison with the state-of-the-art approaches.
关键词	Super-resolution Gradient Magnitude Transformation Linear Transformation Function
WOS标题词	Science & Technology ; Technology
DOI	10.1007/s11042-016-3656-z
关键词[WOS]	RECONSTRUCTION ; LIMITS
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61263046 ; 61403376 ; 61175025)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000400570400048
引用统计	被引频次：5[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/173211/15262
专题	多模态人工智能系统全国重点实验室_先进时空数据分析与学习
作者单位	1.Nanchang Hangkong Univ, Inst Comp Vis, Nanchang, Jiangxi, Peoples R China 2.Nanchang Hangkong Univ, Key Laborator Jiangxi Prov Image Proc & Pattern R, Nanchang, Jiangxi, Peoples R China 3.Chinese Acad Sci, Inst Automat, NLPR, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Han, Wei,Chu, Jun,Wang, Lingfeng,et al. Edge-directed single image super-resolution via cross-resolution sharpening function learning[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2017,76(8):11143-11155.
APA	Han, Wei,Chu, Jun,Wang, Lingfeng,&Pan, Chunhong.(2017).Edge-directed single image super-resolution via cross-resolution sharpening function learning.MULTIMEDIA TOOLS AND APPLICATIONS,76(8),11143-11155.
MLA	Han, Wei,et al."Edge-directed single image super-resolution via cross-resolution sharpening function learning".MULTIMEDIA TOOLS AND APPLICATIONS 76.8(2017):11143-11155.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
1-5.pdf（5043KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载