UM
Fast removal of rain streaks from a single image via a shape prior
Luo Y.3; Zhu J.3; Ling J.3; Wu E.2
2018
Source PublicationIEEE Access
ISSN21693536
Volume6Pages:60069-60078
AbstractRecently, single-image rain removal has attracted sustained attention. In this paper, we utilize a simple shape prior, the fact that the rain streaks often appear in an elongated elliptical shape, in a particular way for single image de-raining. With this prior, the patches of the rain layer are forced to have a high correlation with our synthetic ellipse matrix. Then, the rain layer is refined during each layer decomposition process with the correlation constraints. The experiments show that the proposed method outperforms the existing single image de-raining methods on both real and synthetic data. Moreover, our approach runs much faster than the other state-of-the-art de-raining methods.
Keywordlayer decomposition rain removal Shape prior
DOI10.1109/ACCESS.2018.2875171
URLView the original
Language英語
Fulltext Access
Citation statistics
Document TypeJournal article
CollectionUniversity of Macau
Affiliation1.Institute of Software Chinese Academy of Sciences
2.Universidade de Macau
3.Guangdong University of Technology
Recommended Citation
GB/T 7714
Luo Y.,Zhu J.,Ling J.,et al. Fast removal of rain streaks from a single image via a shape prior[J]. IEEE Access,2018,6:60069-60078.
APA Luo Y.,Zhu J.,Ling J.,&Wu E..(2018).Fast removal of rain streaks from a single image via a shape prior.IEEE Access,6,60069-60078.
MLA Luo Y.,et al."Fast removal of rain streaks from a single image via a shape prior".IEEE Access 6(2018):60069-60078.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Luo Y.]'s Articles
[Zhu J.]'s Articles
[Ling J.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Luo Y.]'s Articles
[Zhu J.]'s Articles
[Ling J.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Luo Y.]'s Articles
[Zhu J.]'s Articles
[Ling J.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.