Blind image deblurring using dark channel prior

Jinshan Pan, Deqing Sun, Hanspeter Pfister, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

182 Citations (Scopus)

Abstract

We present a simple and effective blind image deblurring method based on the dark channel prior. Our work is inspired by the interesting observation that the dark channel of blurred images is less sparse. While most image patches in the clean image contain some dark pixels, these pixels are not dark when averaged with neighboring highintensity pixels during the blur process. This change in the sparsity of the dark channel is an inherent property of the blur process, which we both prove mathematically and validate using training data. Therefore, enforcing the sparsity of the dark channel helps blind deblurring on various scenarios, including natural, face, text, and low-illumination images. However, sparsity of the dark channel introduces a non-convex non-linear optimization problem. We introduce a linear approximation of the min operator to compute the dark channel. Our look-up-table-based method converges fast in practice and can be directly extended to non-uniform deblurring. Extensive experiments show that our method achieves state-of-the-art results on deblurring natural images and compares favorably methods that are well-engineered for specific scenarios.

Original languageEnglish
Title of host publicationProceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PublisherIEEE Computer Society
Pages1628-1636
Number of pages9
ISBN (Electronic)9781467388504
DOIs
Publication statusPublished - 2016 Dec 9
Event29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States
Duration: 2016 Jun 262016 Jul 1

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2016-December
ISSN (Print)1063-6919

Conference

Conference29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
CountryUnited States
CityLas Vegas
Period16/6/2616/7/1

Fingerprint

Pixels
Lighting
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Pan, J., Sun, D., Pfister, H., & Yang, M. H. (2016). Blind image deblurring using dark channel prior. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (pp. 1628-1636). [7780549] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December). IEEE Computer Society. https://doi.org/10.1109/CVPR.2016.180
Pan, Jinshan ; Sun, Deqing ; Pfister, Hanspeter ; Yang, Ming Hsuan. / Blind image deblurring using dark channel prior. Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. pp. 1628-1636 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{dcb8a14adbce4f34bc5c103e662fe345,
title = "Blind image deblurring using dark channel prior",
abstract = "We present a simple and effective blind image deblurring method based on the dark channel prior. Our work is inspired by the interesting observation that the dark channel of blurred images is less sparse. While most image patches in the clean image contain some dark pixels, these pixels are not dark when averaged with neighboring highintensity pixels during the blur process. This change in the sparsity of the dark channel is an inherent property of the blur process, which we both prove mathematically and validate using training data. Therefore, enforcing the sparsity of the dark channel helps blind deblurring on various scenarios, including natural, face, text, and low-illumination images. However, sparsity of the dark channel introduces a non-convex non-linear optimization problem. We introduce a linear approximation of the min operator to compute the dark channel. Our look-up-table-based method converges fast in practice and can be directly extended to non-uniform deblurring. Extensive experiments show that our method achieves state-of-the-art results on deblurring natural images and compares favorably methods that are well-engineered for specific scenarios.",
author = "Jinshan Pan and Deqing Sun and Hanspeter Pfister and Yang, {Ming Hsuan}",
year = "2016",
month = "12",
day = "9",
doi = "10.1109/CVPR.2016.180",
language = "English",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "1628--1636",
booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",
address = "United States",

}

Pan, J, Sun, D, Pfister, H & Yang, MH 2016, Blind image deblurring using dark channel prior. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016., 7780549, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, IEEE Computer Society, pp. 1628-1636, 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 16/6/26. https://doi.org/10.1109/CVPR.2016.180

Blind image deblurring using dark channel prior. / Pan, Jinshan; Sun, Deqing; Pfister, Hanspeter; Yang, Ming Hsuan.

Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. p. 1628-1636 7780549 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Blind image deblurring using dark channel prior

AU - Pan, Jinshan

AU - Sun, Deqing

AU - Pfister, Hanspeter

AU - Yang, Ming Hsuan

PY - 2016/12/9

Y1 - 2016/12/9

N2 - We present a simple and effective blind image deblurring method based on the dark channel prior. Our work is inspired by the interesting observation that the dark channel of blurred images is less sparse. While most image patches in the clean image contain some dark pixels, these pixels are not dark when averaged with neighboring highintensity pixels during the blur process. This change in the sparsity of the dark channel is an inherent property of the blur process, which we both prove mathematically and validate using training data. Therefore, enforcing the sparsity of the dark channel helps blind deblurring on various scenarios, including natural, face, text, and low-illumination images. However, sparsity of the dark channel introduces a non-convex non-linear optimization problem. We introduce a linear approximation of the min operator to compute the dark channel. Our look-up-table-based method converges fast in practice and can be directly extended to non-uniform deblurring. Extensive experiments show that our method achieves state-of-the-art results on deblurring natural images and compares favorably methods that are well-engineered for specific scenarios.

AB - We present a simple and effective blind image deblurring method based on the dark channel prior. Our work is inspired by the interesting observation that the dark channel of blurred images is less sparse. While most image patches in the clean image contain some dark pixels, these pixels are not dark when averaged with neighboring highintensity pixels during the blur process. This change in the sparsity of the dark channel is an inherent property of the blur process, which we both prove mathematically and validate using training data. Therefore, enforcing the sparsity of the dark channel helps blind deblurring on various scenarios, including natural, face, text, and low-illumination images. However, sparsity of the dark channel introduces a non-convex non-linear optimization problem. We introduce a linear approximation of the min operator to compute the dark channel. Our look-up-table-based method converges fast in practice and can be directly extended to non-uniform deblurring. Extensive experiments show that our method achieves state-of-the-art results on deblurring natural images and compares favorably methods that are well-engineered for specific scenarios.

UR - http://www.scopus.com/inward/record.url?scp=84986327379&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986327379&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2016.180

DO - 10.1109/CVPR.2016.180

M3 - Conference contribution

AN - SCOPUS:84986327379

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 1628

EP - 1636

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

ER -

Pan J, Sun D, Pfister H, Yang MH. Blind image deblurring using dark channel prior. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society. 2016. p. 1628-1636. 7780549. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2016.180