OPT OpenIR  > 光学影像学习与分析中心
Nonlocal patch based T-SVD for image inpainting: Algorithm and error analysis
Song, Liangchen1,2; Du, Bo1; Zhang, Lefei1; Zhang, Liangpei2; Wu, Jia3; Li, Xuelong4
2018
Conference Name32nd AAAI Conference on Artificial Intelligence, AAAI 2018
Source Publication32nd AAAI Conference on Artificial Intelligence, AAAI 2018
Pages2419-2426
Conference Date2018-02-02
Conference PlaceNew Orleans, LA, United states
PublisherAAAI press
Contribution Rank4
Abstract

In this paper, we propose a novel image inpainting framework consisting of an interpolation step and a low-rank tensor completion step. More specifically, we first initial the image with triangulation-based linear interpolation, and then we find similar patches for each missing-entry centered patch. Treating a group of patch matrices as a tensor, we employ the recently proposed effective t-SVD tensor completion algorithm with a warm start strategy to inpaint it. We observe that the interpolation step is such a rough initialization that the similar patch we found may not exactly match with the reference, so we name the problem as Patch Mismatch and analyse the error caused by it thoroughly. Our theoretical analysis shows that the error caused by Patch Mismatch can be decomposed into two components, one of which can be bounded by a reasonable assumption named local patch similarity, and another part is lower than that using matrix. Experiments on real images verify our method's superiority to the state-of-the-art inpainting methods. Copyright © 2018, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Department光学影像学习与分析中心
Indexed ByEI
ISBN9781577358008
Language英语
EI Accession Number20190506436068
Document Type会议论文
Identifierhttp://ir.opt.ac.cn/handle/181661/31242
Collection光学影像学习与分析中心
Affiliation1.School of Computer Science, Wuhan University, Wuhan; 430079, China;
2.State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan; 430079, China;
3.Department of Computing, Macquarie University, Sydney; NSW; 2109, Australia;
4.Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an; 710119, China
Recommended Citation
GB/T 7714
Song, Liangchen,Du, Bo,Zhang, Lefei,et al. Nonlocal patch based T-SVD for image inpainting: Algorithm and error analysis[C]:AAAI press,2018:2419-2426.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Song, Liangchen]'s Articles
[Du, Bo]'s Articles
[Zhang, Lefei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Song, Liangchen]'s Articles
[Du, Bo]'s Articles
[Zhang, Lefei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Song, Liangchen]'s Articles
[Du, Bo]'s Articles
[Zhang, Lefei]'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.