Nonlocal patch based t-SVD for image inpainting

algorithm and error analysis

Liangchen Song, Bo Du*, Lefei Zhang, Liangpei Zhang, Jia Wu, Xuelong Li

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

1 Citation (Scopus)

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.

Original languageEnglish
Title of host publication32nd AAAI Conference on Artificial Intelligence, AAAI 2018
Place of PublicationMenlo Park, California
PublisherAssociation for the Advancement of Artificial Intelligence
Pages2419-2426
Number of pages8
ISBN (Electronic)9781577358008
Publication statusPublished - 1 Jan 2018
Event32nd AAAI Conference on Artificial Intelligence, AAAI 2018 - New Orleans, United States
Duration: 2 Feb 20187 Feb 2018

Conference

Conference32nd AAAI Conference on Artificial Intelligence, AAAI 2018
CountryUnited States
CityNew Orleans
Period2/02/187/02/18

Fingerprint Dive into the research topics of 'Nonlocal patch based t-SVD for image inpainting: algorithm and error analysis'. Together they form a unique fingerprint.

  • Cite this

    Song, L., Du, B., Zhang, L., Zhang, L., Wu, J., & Li, X. (2018). Nonlocal patch based t-SVD for image inpainting: algorithm and error analysis. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 (pp. 2419-2426). Menlo Park, California: Association for the Advancement of Artificial Intelligence.