Skip to main navigation Skip to search Skip to main content

Guaranteed Matrix Completion under Multiple Linear Transformations

  • Chao Li
  • , Wei He
  • , Longhao Yuan
  • , Zhun Sun
  • , Qibin Zhao*
  • *Corresponding author for this work
  • RIKEN
  • Saitama Inst Technol
  • Guangdong Univ Technol

Research output: Contribution to journal › Conference article › peer-review

12 Scopus citations

Abstract

Low-rank matrix completion (LRMC) is a classical model in both computer vision (CV) and machine learning, and has been successfully applied to various real applications. In the recent CV tasks, the completion is usually employed on the variants of data, such as "non-local" or filtered, rather than their original forms. This fact makes that the theoretical analysis of the conventional LRMC is no longer suitable in these applications. To tackle this problem, we propose a more general framework for LRMC, in which the linear transformations of the data are taken into account. We rigorously prove the identifiability of the proposed model and show an upper bound of the reconstruction error. Furthermore, we derive an efficient completion algorithm by using augmented Lagrangian multipliers and the sketching trick. In the experiments, we apply the proposed method to the classical image inpainting problem and achieve the state-of-the-art results.
Original languageEnglish
Pages (from-to)11128-11137
Number of pages10
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
StatePublished - 16 Jun 2019
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) - Long Beach,CA, Long Beach, Canada
Duration: 16 Jun 2019 → 20 Jun 2019

Funding

This work is partially supported by JSPS KAKENHI (Grant No. 17K00326) and NSFC China (Grant No. 61773129).

Indexed by

  • CPCI-S

Fingerprint

Dive into the research topics of 'Guaranteed Matrix Completion under Multiple Linear Transformations'. Together they form a unique fingerprint.

Cite this