Video super-resolution using low rank matrix completion

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

4 Citations (Scopus)

Abstract

In this paper, a novel video super-resolution image reconstruction algorithm is proposed. We design a patch-based low rank matrix completion algorithm. The proposed algorithm addresses the problem of generating a high-resolution (HR) image from several low-resolution (LR) images, based on sparse representation and low-rank matrix completion. The approach represents observed LR frames in the form of sparse matrices and rearranges those frames into low dimensional constructions. Experimental results demonstrate that, high-frequency details in the super resolved images are recovered from the LR frames. The gains in terms of PSNR and SSIM are significant.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
Pages1376-1380
Number of pages5
DOIs
Publication statusPublished - 1 Dec 2013
Event2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, United Kingdom
Duration: 15 Sep 201318 Sep 2013

Conference

Conference2013 20th IEEE International Conference on Image Processing, ICIP 2013
CountryUnited Kingdom
CityMelbourne, VIC
Period15/09/1318/09/13

Keywords

  • Low-rank Matrix Completion
  • Singular Value Thresholding
  • Video Super-Resolution

Fingerprint

Dive into the research topics of 'Video super-resolution using low rank matrix completion'. Together they form a unique fingerprint.

Cite this