Coarse-to-Fine Learning for Single-Image Super-Resolution | |
Zhang, Kaibing1; Tao, Dacheng2,3; Gao, Xinbo4; Li, Xuelong5; Li, Jie6; Zhang, KB (reprint author), Hubei Engn Univ, Sch Comp & Informat Sci, Xiaogan 432000, Hubei, Peoples R China. | |
作者部门 | 光学影像学习与分析中心 |
2017-05-01 | |
发表期刊 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS |
ISSN | 2162-237X |
卷号 | 28期号:5页码:1109-1122 |
产权排序 | 5 |
摘要 | This paper develops a coarse-to-fine framework for single-image super-resolution (SR) reconstruction. The coarse-to-fine approach achieves high-quality SR recovery based on the complementary properties of both example learning- and reconstruction-based algorithms: example learning-based SR approaches are useful for generating plausible details from external exemplars but poor at suppressing aliasing artifacts, while reconstruction-based SR methods are propitious for preserving sharp edges yet fail to generate fine details. In the coarse stage of the method, we use a set of simple yet effective mapping functions, learned via correlative neighbor regression of grouped low-resolution (LR) to high-resolution (HR) dictionary atoms, to synthesize an initial SR estimate with particularly low computational cost. In the fine stage, we devise an effective regularization term that seamlessly integrates the properties of local structural regularity, nonlocal self-similarity, and collaborative representation over relevant atoms in a learned HR dictionary, to further improve the visual quality of the initial SR estimation obtained in the coarse stage. The experimental results indicate that our method outperforms other state-of-the-art methods for producing high-quality images despite that both the initial SR estimation and the followed enhancement are cheap to implement. |
文章类型 | Article |
关键词 | Correlative Neighbor Regression (Cnr) Nonlocal Means Regularization Term Self-similarity Single-image Super-resolution (Sr) |
学科领域 | Computer Science, Artificial Intelligence |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1109/TNNLS.2015.2511069 |
收录类别 | SCI ; EI |
关键词[WOS] | SPARSE REPRESENTATION ; KERNEL REGRESSION ; INTERPOLATION ; FRAMEWORK ; ALGORITHM ; RECONSTRUCTION ; REGULARIZATION |
语种 | 英语 |
WOS研究方向 | Computer Science ; Engineering |
项目资助者 | Key Research Program within Chinese Academy of Sciences(KGZD-EW-T03) ; National Natural Science Foundation of China(61471161 ; Fundamental Research Funds for the Central Universities(BDZ021403 ; Program for Changjiang Scholars and Innovative Research Team in University of China(IRT13088) ; China Post-Doctoral Science Foundation(2013M540734 ; Australian Research Council(DP-140102164 ; Hubei Provincial Department of Education Outstanding Youth Scientific Innovation Team Support Foundation(T201410) ; 61432014 ; JB149901) ; 2014T70905) ; FT-130101457) ; 61370092 ; 61572388) |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000401981800008 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/28982 |
专题 | 光谱成像技术研究室 |
通讯作者 | Zhang, KB (reprint author), Hubei Engn Univ, Sch Comp & Informat Sci, Xiaogan 432000, Hubei, Peoples R China. |
作者单位 | 1.Hubei Engn Univ, Sch Comp & Informat Sci, Xiaogan 432000, Hubei, Peoples R China 2.Univ Technol Sydney, Ctr Quantum Computat & Intelligent Syst, 81 Broadway St, Ultimo, NSW 2007, Australia 3.Univ Technol Sydney, Fac Engn & Informat Technol, 81 Broadway St, Ultimo, NSW 2007, Australia 4.Xidian Univ, State Key Lab Integrated Serv Networks, Sch Elect Engn, Xian 710071, Shaanxi, Peoples R China 5.Chinese Acad Sci, Ctr OPT IMagery Anal & Learning OPTIMAL, State Key Lab Transient Opt & Photon, Xian Inst Opt & Precis Mech, Xian 710119, Shaanxi, Peoples R China 6.Xidian Univ, Video & Image Proc Syst Lab, Sch Elect Engn, Xian 710071, Shaanxi, Peoples R China |
推荐引用方式 GB/T 7714 | Zhang, Kaibing,Tao, Dacheng,Gao, Xinbo,et al. Coarse-to-Fine Learning for Single-Image Super-Resolution[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2017,28(5):1109-1122. |
APA | Zhang, Kaibing,Tao, Dacheng,Gao, Xinbo,Li, Xuelong,Li, Jie,&Zhang, KB .(2017).Coarse-to-Fine Learning for Single-Image Super-Resolution.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,28(5),1109-1122. |
MLA | Zhang, Kaibing,et al."Coarse-to-Fine Learning for Single-Image Super-Resolution".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 28.5(2017):1109-1122. |
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 | ||
Coarse-to-Fine Learn(3110KB) | 期刊论文 | 作者接受稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论