期刊
IEEE TRANSACTIONS ON CYBERNETICS
卷 51, 期 2, 页码 673-685出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2019.2910151
关键词
Image inpainting; low-rank tensor completion; tensor nuclear norm (TNN); visual data completion
类别
资金
- National Natural Science Foundation of China [61771349, 61822113, U1536204]
- National Key Research and Development Program of China [2018YFA0605501]
The paper introduces a novel nonlocal patch tensor-based visual data completion algorithm, addressing the problem of patch mismatch by decomposing the patch tensor into low-rank and sparse tensors. This method effectively completes images by utilizing the tensor completion technique, demonstrating superiority over existing tensor-based image inpainting methods in experimental results on real-world datasets.
In this paper, we propose a novel nonlocal patch tensor-based visual data completion algorithm and analyze its potential problems. Our algorithm consists of two steps: the first step is initializing the image with triangulation-based linear interpolation and the second step is grouping similar nonlocal patches as a tensor then applying the proposed tensor completion technique. Specifically, with treating a group of patch matrices as a tensor, we impose the low-rank constraint on the tensor through the recently proposed tensor nuclear norm. Moreover, we observe that after the first interpolation step, the image gets blurred and, thus, the similar patches we have found may not exactly match the reference. We name the problem Patch Mismatch, and then in order to avoid the error caused by it, we further decompose the patch tensor into a low-rank tensor and a sparse tensor, which means the accepted horizontal strips in mismatched patches. Furthermore, 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 the other part is lower than that using matrix completion. Extensive experimental results on real-world datasets verify our method's superiority to the state-of-the-art tensor-based image inpainting methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据