Video super-resolution using low rank matrix completion

Jin Chen; Jose Nunez-Yanez; Alin Achim

doi:10.1109/ICIP.2013.6738283

Video super-resolution using low rank matrix completion

Jin Chen, Jose Nunez-Yanez, Alin Achim

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English
Title of host publication	2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
Pages	1376-1380
Number of pages	5
DOIs	https://doi.org/10.1109/ICIP.2013.6738283
Publication status	Published - 1 Dec 2013
Event	2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, United Kingdom Duration: 15 Sept 2013 → 18 Sept 2013

Conference

Conference	2013 20th IEEE International Conference on Image Processing, ICIP 2013
Country/Territory	United Kingdom
City	Melbourne, VIC
Period	15/09/13 → 18/09/13

Keywords

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

Access to Document

10.1109/ICIP.2013.6738283

Handle.net

Persistent link

Cite this

@inproceedings{47521864006f4f118e31034c6d9873fb,

title = "Video super-resolution using low rank matrix completion",

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.",

keywords = "Low-rank Matrix Completion, Singular Value Thresholding, Video Super-Resolution",

author = "Jin Chen and Jose Nunez-Yanez and Alin Achim",

year = "2013",

month = dec,

day = "1",

doi = "10.1109/ICIP.2013.6738283",

language = "English",

isbn = "9781479923410",

pages = "1376--1380",

booktitle = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

note = "2013 20th IEEE International Conference on Image Processing, ICIP 2013 ; Conference date: 15-09-2013 Through 18-09-2013",

}

TY - GEN

T1 - Video super-resolution using low rank matrix completion

AU - Chen, Jin

AU - Nunez-Yanez, Jose

AU - Achim, Alin

PY - 2013/12/1

Y1 - 2013/12/1

N2 - 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.

AB - 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.

KW - Low-rank Matrix Completion

KW - Singular Value Thresholding

KW - Video Super-Resolution

UR - http://www.scopus.com/inward/record.url?scp=84897764391&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2013.6738283

DO - 10.1109/ICIP.2013.6738283

M3 - Conference Contribution (Conference Proceeding)

AN - SCOPUS:84897764391

SN - 9781479923410

SP - 1376

EP - 1380

BT - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

T2 - 2013 20th IEEE International Conference on Image Processing, ICIP 2013

Y2 - 15 September 2013 through 18 September 2013

ER -

Video super-resolution using low rank matrix completion

Abstract

Conference

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this