High dynamic range imaging via truncated nuclear norm minimization of low-rank matrix

Chul Lee; Edmund Y. Lam

doi:10.1109/ICASSP.2016.7471872

High dynamic range imaging via truncated nuclear norm minimization of low-rank matrix

Chul Lee, Edmund Y. Lam

Department of Computer Science and Artificial Intelligence

The University of Hong Kong

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

We propose a ghost-free high dynamic range (HDR) image synthesis algorithm using a rank minimization framework. Based on the linear dependency among irradiance maps from low dynamic range (LDR) images, we formulate ghost-free HDR imaging as a low-rank matrix completion problem. The main contribution is to solve it efficiently via the augmented Lagrange multiplier (ALM) method, where the optimization variables are updated by closed-form solutions. Experiments on real image sets show that the proposed algorithm provides comparable or even better image qualities than state-of-the-art approaches, while demanding lower computational resources.

Original language	English
Title of host publication	2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1229-1233
Number of pages	5
ISBN (Electronic)	9781479999880
DOIs	https://doi.org/10.1109/ICASSP.2016.7471872
State	Published - 18 May 2016
Event	41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China Duration: 20 Mar 2016 → 25 Mar 2016

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2016-May
ISSN (Print)	1520-6149

Conference

Conference	41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
Country/Territory	China
City	Shanghai
Period	20/03/16 → 25/03/16

Keywords

High dynamic range imaging
low-rank matrix completion
truncated nuclear norm minimization

Access to Document

10.1109/ICASSP.2016.7471872

Cite this

Lee, C., & Lam, E. Y. (2016). High dynamic range imaging via truncated nuclear norm minimization of low-rank matrix. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings (pp. 1229-1233). Article 7471872 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2016-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2016.7471872

Lee, Chul ; Lam, Edmund Y. / High dynamic range imaging via truncated nuclear norm minimization of low-rank matrix. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1229-1233 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{dbe7dbe62874404fbc93be1261f83ae8,

title = "High dynamic range imaging via truncated nuclear norm minimization of low-rank matrix",

abstract = "We propose a ghost-free high dynamic range (HDR) image synthesis algorithm using a rank minimization framework. Based on the linear dependency among irradiance maps from low dynamic range (LDR) images, we formulate ghost-free HDR imaging as a low-rank matrix completion problem. The main contribution is to solve it efficiently via the augmented Lagrange multiplier (ALM) method, where the optimization variables are updated by closed-form solutions. Experiments on real image sets show that the proposed algorithm provides comparable or even better image qualities than state-of-the-art approaches, while demanding lower computational resources.",

keywords = "High dynamic range imaging, low-rank matrix completion, truncated nuclear norm minimization",

author = "Chul Lee and Lam, {Edmund Y.}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 ; Conference date: 20-03-2016 Through 25-03-2016",

year = "2016",

month = may,

day = "18",

doi = "10.1109/ICASSP.2016.7471872",

language = "English",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1229--1233",

booktitle = "2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings",

address = "United States",

}

Lee, C & Lam, EY 2016, High dynamic range imaging via truncated nuclear norm minimization of low-rank matrix. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings., 7471872, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2016-May, Institute of Electrical and Electronics Engineers Inc., pp. 1229-1233, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 20/03/16. https://doi.org/10.1109/ICASSP.2016.7471872

High dynamic range imaging via truncated nuclear norm minimization of low-rank matrix. / Lee, Chul; Lam, Edmund Y.
2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1229-1233 7471872 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2016-May).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - High dynamic range imaging via truncated nuclear norm minimization of low-rank matrix

AU - Lee, Chul

AU - Lam, Edmund Y.

PY - 2016/5/18

Y1 - 2016/5/18

N2 - We propose a ghost-free high dynamic range (HDR) image synthesis algorithm using a rank minimization framework. Based on the linear dependency among irradiance maps from low dynamic range (LDR) images, we formulate ghost-free HDR imaging as a low-rank matrix completion problem. The main contribution is to solve it efficiently via the augmented Lagrange multiplier (ALM) method, where the optimization variables are updated by closed-form solutions. Experiments on real image sets show that the proposed algorithm provides comparable or even better image qualities than state-of-the-art approaches, while demanding lower computational resources.

AB - We propose a ghost-free high dynamic range (HDR) image synthesis algorithm using a rank minimization framework. Based on the linear dependency among irradiance maps from low dynamic range (LDR) images, we formulate ghost-free HDR imaging as a low-rank matrix completion problem. The main contribution is to solve it efficiently via the augmented Lagrange multiplier (ALM) method, where the optimization variables are updated by closed-form solutions. Experiments on real image sets show that the proposed algorithm provides comparable or even better image qualities than state-of-the-art approaches, while demanding lower computational resources.

KW - High dynamic range imaging

KW - low-rank matrix completion

KW - truncated nuclear norm minimization

UR - http://www.scopus.com/inward/record.url?scp=84973380042&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2016.7471872

DO - 10.1109/ICASSP.2016.7471872

M3 - Conference contribution

AN - SCOPUS:84973380042

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 1229

EP - 1233

BT - 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016

Y2 - 20 March 2016 through 25 March 2016

ER -

Lee C, Lam EY. High dynamic range imaging via truncated nuclear norm minimization of low-rank matrix. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1229-1233. 7471872. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2016.7471872

High dynamic range imaging via truncated nuclear norm minimization of low-rank matrix

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this