Extending Continuous Cuts: Anisotropic Metrics and Expansion Moves
(2009) IEEE International Conference on Computer Vision (ICCV), 2009 p.405-412- Abstract
- The concept of graph cuts is by now a standard method for all sorts of low level vision problems. Its popularity is largely due to the fact that globally or near globally optimal solutions can be computed using efficient max flow algorithms. On the other hand it has been observed that this method may suffer from metrication errors. Recent work has begun studying continuous versions of graph cuts, which give smaller metrication errors. Another advantage is that continuous cuts are straightforward to parallelize. In this paper we extend the class of functionals that can be optimized in the continuous setting to include anisotropic TV-norms. We show that there is a so called coarea formula for these functionals making it possible to minimize... (More)
- The concept of graph cuts is by now a standard method for all sorts of low level vision problems. Its popularity is largely due to the fact that globally or near globally optimal solutions can be computed using efficient max flow algorithms. On the other hand it has been observed that this method may suffer from metrication errors. Recent work has begun studying continuous versions of graph cuts, which give smaller metrication errors. Another advantage is that continuous cuts are straightforward to parallelize. In this paper we extend the class of functionals that can be optimized in the continuous setting to include anisotropic TV-norms. We show that there is a so called coarea formula for these functionals making it possible to minimize them by solving a convex problem. We also show that the concept of α-expansion moves can be reformulated to fit the continuous formulation, and we derive approximation bounds in analogy with the discrete case. A continuous version of the Potts model for multi-class segmentation problems is presented, and it is shown how to obtain provably good solutions using continuous α-expansions. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1687617
- author
- Olsson, Carl LU ; Byröd, Martin LU ; Overgaard, Niels Christian LU and Kahl, Fredrik LU
- organization
- publishing date
- 2009
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Proceedings of 2009 IEEE 12th International Conference on Computer Vision (ICCV)
- pages
- 8 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- IEEE International Conference on Computer Vision (ICCV), 2009
- conference location
- Kyoto, Japan
- conference dates
- 2009-09-27 - 2009-10-04
- external identifiers
-
- wos:000294955300052
- scopus:77953225317
- ISBN
- 978-1-4244-4419-9
- DOI
- 10.1109/ICCV.2009.5459206
- language
- English
- LU publication?
- yes
- id
- e8298764-3d96-4f6e-9948-6e790405ff11 (old id 1687617)
- date added to LUP
- 2016-04-04 11:58:02
- date last changed
- 2022-04-24 01:28:52
@inproceedings{e8298764-3d96-4f6e-9948-6e790405ff11,
abstract = {{The concept of graph cuts is by now a standard method for all sorts of low level vision problems. Its popularity is largely due to the fact that globally or near globally optimal solutions can be computed using efficient max flow algorithms. On the other hand it has been observed that this method may suffer from metrication errors. Recent work has begun studying continuous versions of graph cuts, which give smaller metrication errors. Another advantage is that continuous cuts are straightforward to parallelize. In this paper we extend the class of functionals that can be optimized in the continuous setting to include anisotropic TV-norms. We show that there is a so called coarea formula for these functionals making it possible to minimize them by solving a convex problem. We also show that the concept of α-expansion moves can be reformulated to fit the continuous formulation, and we derive approximation bounds in analogy with the discrete case. A continuous version of the Potts model for multi-class segmentation problems is presented, and it is shown how to obtain provably good solutions using continuous α-expansions.}},
author = {{Olsson, Carl and Byröd, Martin and Overgaard, Niels Christian and Kahl, Fredrik}},
booktitle = {{Proceedings of 2009 IEEE 12th International Conference on Computer Vision (ICCV)}},
isbn = {{978-1-4244-4419-9}},
language = {{eng}},
pages = {{405--412}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
title = {{Extending Continuous Cuts: Anisotropic Metrics and Expansion Moves}},
url = {{http://dx.doi.org/10.1109/ICCV.2009.5459206}},
doi = {{10.1109/ICCV.2009.5459206}},
year = {{2009}},
}