Nonlocal patch based T-SVD for image inpainting: Algorithm and error analysis

Song, L; Du, B; Zhang, L; Wu, J; Li, X

Nonlocal patch based T-SVD for image inpainting: Algorithm and error analysis

Song, L Du, B Zhang, L Wu, J Li, X

Permalink

Publication Type:: Conference Proceeding
Citation:: 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, 2018, pp. 2419 - 2426
Issue Date:: 2018-01-01

Closed Access

	Filename	Description	Size
	16663-76718-1-PB.pdf	Published version	1.87 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Song, L	en_US
dc.contributor.author	Du, B	en_US
dc.contributor.author	Zhang, L	en_US
dc.contributor.author	Wu, J	en_US
dc.contributor.author	Li, X	en_US
dc.date.issued	2018-01-01	en_US
dc.identifier.citation	32nd AAAI Conference on Artificial Intelligence, AAAI 2018, 2018, pp. 2419 - 2426	en_US
dc.identifier.isbn	9781577358008	en_US
dc.identifier.uri	http://hdl.handle.net/10453/133659
dc.description.abstract	Copyright © 2018, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. 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.	en_US
dc.relation.ispartof	32nd AAAI Conference on Artificial Intelligence, AAAI 2018	en_US
dc.title	Nonlocal patch based T-SVD for image inpainting: Algorithm and error analysis	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

Copyright © 2018, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. 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.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/133659