Iteratively reweighted graph cut for multi-label MRFs with non-convex priors

Thalaiyasingam Ajanthan; Richard Hartley; Mathieu Salzmann; Hongdong Li

doi:10.1109/CVPR.2015.7299150

Iteratively reweighted graph cut for multi-label MRFs with non-convex priors

Thalaiyasingam Ajanthan, Richard Hartley, Mathieu Salzmann, Hongdong Li

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

7 Citations (Scopus)

Abstract

While widely acknowledged as highly effective in computer vision, multi-label MRFs with non-convex priors are difficult to optimize. To tackle this, we introduce an algorithm that iteratively approximates the original energy with an appropriately weighted surrogate energy that is easier to minimize. Our algorithm guarantees that the original energy decreases at each iteration. In particular, we consider the scenario where the global minimizer of the weighted surrogate energy can be obtained by a multi-label graph cut algorithm, and show that our algorithm then lets us handle of large variety of non-convex priors. We demonstrate the benefits of our method over state-of-the-art MRF energy minimization techniques on stereo and inpainting problems.

Original language	English
Title of host publication	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Publisher	IEEE Computer Society
Pages	5144-5152
Number of pages	9
ISBN (Electronic)	9781467369640
DOIs	https://doi.org/10.1109/CVPR.2015.7299150
Publication status	Published - 14 Oct 2015
Event	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States Duration: 7 Jun 2015 → 12 Jun 2015

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	07-12-June-2015
ISSN (Print)	1063-6919

Conference

Conference	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Country/Territory	United States
City	Boston
Period	7/06/15 → 12/06/15

Access to Document

10.1109/CVPR.2015.7299150

Cite this

Ajanthan, T., Hartley, R., Salzmann, M., & Li, H. (2015). Iteratively reweighted graph cut for multi-label MRFs with non-convex priors. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (pp. 5144-5152). Article 7299150 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7299150

@inproceedings{117eb14720a14a83aa343ea4f26c231f,

title = "Iteratively reweighted graph cut for multi-label MRFs with non-convex priors",

abstract = "While widely acknowledged as highly effective in computer vision, multi-label MRFs with non-convex priors are difficult to optimize. To tackle this, we introduce an algorithm that iteratively approximates the original energy with an appropriately weighted surrogate energy that is easier to minimize. Our algorithm guarantees that the original energy decreases at each iteration. In particular, we consider the scenario where the global minimizer of the weighted surrogate energy can be obtained by a multi-label graph cut algorithm, and show that our algorithm then lets us handle of large variety of non-convex priors. We demonstrate the benefits of our method over state-of-the-art MRF energy minimization techniques on stereo and inpainting problems.",

author = "Thalaiyasingam Ajanthan and Richard Hartley and Mathieu Salzmann and Hongdong Li",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 ; Conference date: 07-06-2015 Through 12-06-2015",

year = "2015",

month = oct,

day = "14",

doi = "10.1109/CVPR.2015.7299150",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "5144--5152",

booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",

address = "United States",

}

Ajanthan, T, Hartley, R, Salzmann, M & Li, H 2015, Iteratively reweighted graph cut for multi-label MRFs with non-convex priors. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7299150, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE Computer Society, pp. 5144-5152, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 7/06/15. https://doi.org/10.1109/CVPR.2015.7299150

Iteratively reweighted graph cut for multi-label MRFs with non-convex priors. / Ajanthan, Thalaiyasingam; Hartley, Richard; Salzmann, Mathieu et al.
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. p. 5144-5152 7299150 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

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

TY - GEN

T1 - Iteratively reweighted graph cut for multi-label MRFs with non-convex priors

AU - Ajanthan, Thalaiyasingam

AU - Hartley, Richard

AU - Salzmann, Mathieu

AU - Li, Hongdong

PY - 2015/10/14

Y1 - 2015/10/14

N2 - While widely acknowledged as highly effective in computer vision, multi-label MRFs with non-convex priors are difficult to optimize. To tackle this, we introduce an algorithm that iteratively approximates the original energy with an appropriately weighted surrogate energy that is easier to minimize. Our algorithm guarantees that the original energy decreases at each iteration. In particular, we consider the scenario where the global minimizer of the weighted surrogate energy can be obtained by a multi-label graph cut algorithm, and show that our algorithm then lets us handle of large variety of non-convex priors. We demonstrate the benefits of our method over state-of-the-art MRF energy minimization techniques on stereo and inpainting problems.

AB - While widely acknowledged as highly effective in computer vision, multi-label MRFs with non-convex priors are difficult to optimize. To tackle this, we introduce an algorithm that iteratively approximates the original energy with an appropriately weighted surrogate energy that is easier to minimize. Our algorithm guarantees that the original energy decreases at each iteration. In particular, we consider the scenario where the global minimizer of the weighted surrogate energy can be obtained by a multi-label graph cut algorithm, and show that our algorithm then lets us handle of large variety of non-convex priors. We demonstrate the benefits of our method over state-of-the-art MRF energy minimization techniques on stereo and inpainting problems.

UR - http://www.scopus.com/inward/record.url?scp=84959235539&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7299150

DO - 10.1109/CVPR.2015.7299150

M3 - Conference contribution

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

SP - 5144

EP - 5152

BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

PB - IEEE Computer Society

T2 - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

Y2 - 7 June 2015 through 12 June 2015

ER -

Ajanthan T, Hartley R, Salzmann M, Li H. Iteratively reweighted graph cut for multi-label MRFs with non-convex priors. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society. 2015. p. 5144-5152. 7299150. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR.2015.7299150

Iteratively reweighted graph cut for multi-label MRFs with non-convex priors

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this