Hybrid Function Sparse Representation Towards Image Super Resolution
Bian, Junyi1; Lin, Baojun1,2; Zhang, Ke1
2019
会议录名称18TH INTERNATIONAL CONFERENCE ON COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2019
ISSN16113349
卷号11679 LNCS
页码27-37
发表状态已发表
DOI10.1007/978-3-030-29891-3_3
摘要Sparse representation with training-based dictionary has been shown successful on super resolution(SR) but still have some limitations. Based on the idea of making the magnification of function curve without losing its fidelity, we proposed a function based dictionary on sparse representation for super resolution, called hybrid function sparse representation (HFSR). The dictionary we designed is directly generated by preset hybrid functions without additional training, which can be scaled to any size as is required due to its scalable property. We mixed approximated Heaviside function (AHF), sine function and DCT function as the dictionary. Multi-scale refinement is then proposed to utilize the scalable property of the dictionary to improve the results. In addition, a reconstruct strategy is adopted to deal with the overlaps. The experiments on ‘Set14’ SR dataset show that our method has an excellent performance particularly with regards to images containing rich details and contexts compared with non-learning based state-of-the art methods.
© 2019, Springer Nature Switzerland AG.
会议地点Salerno, Italy
URL查看原文
收录类别EI ; CPCI-S ; CPCI
出版者Springer Verlag
EI入藏号20194107502916
EI主题词Optical resolving power
EI分类号Light/Optics:741.1
原始文献类型Conference article (CA)
引用统计
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/89396
专题信息科学与技术学院_硕士生
信息科学与技术学院_特聘教授组_林宝军组
通讯作者Lin, Baojun
作者单位1.ShanghaiTech University, School of Information Science and Technology, Shanghai; 201210, China
2.Chinese Academy of Sciences, Shanghai Engineering Center for Microsatellites, Shanghai; 201203, China
第一作者单位信息科学与技术学院
通讯作者单位信息科学与技术学院
第一作者的第一单位信息科学与技术学院
推荐引用方式
GB/T 7714
Bian, Junyi,Lin, Baojun,Zhang, Ke. Hybrid Function Sparse Representation Towards Image Super Resolution[C]:Springer Verlag,2019:27-37.
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
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Bian, Junyi]的文章
[Lin, Baojun]的文章
[Zhang, Ke]的文章
百度学术
百度学术中相似的文章
[Bian, Junyi]的文章
[Lin, Baojun]的文章
[Zhang, Ke]的文章
必应学术
必应学术中相似的文章
[Bian, Junyi]的文章
[Lin, Baojun]的文章
[Zhang, Ke]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 10.1007@978-3-030-29891-3_3.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

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。