Simultaneous Fusion Moves for 3D-label Stereo
(2013) Energy Minimization Methods in Computer Vision and Pattern Recognition, 9th International Conference, EMMCVPR 2013 Lund, Sweden, August 19-21, 2013 8081. p.80-93- Abstract
- Second derivative regularization methods for dense stereo matching is
a topic of intense research. Some of the most successful recent methods employ so called binary fusion moves where the combination of two proposal solutions is computed. In many cases the fusion move can be solved optimally, but the approach is limited to fusing pairs of proposals in each move. For multiple proposals iterative binary fusion may potentially lead to local minima.
In this paper we demonstrate how to simultaneously fuse more than two proposals at the same time for a 2nd order stereo regularizer. The optimization is made possible by effectively computing a generalized distance transform. This allows for computation of messages in linear time... (More) - Second derivative regularization methods for dense stereo matching is
a topic of intense research. Some of the most successful recent methods employ so called binary fusion moves where the combination of two proposal solutions is computed. In many cases the fusion move can be solved optimally, but the approach is limited to fusing pairs of proposals in each move. For multiple proposals iterative binary fusion may potentially lead to local minima.
In this paper we demonstrate how to simultaneously fuse more than two proposals at the same time for a 2nd order stereo regularizer. The optimization is made possible by effectively computing a generalized distance transform. This allows for computation of messages in linear time in the number of proposals. In addition the approach provides a lower bound on the globally optimal solution of the multi-fusion problem. We verify experimentally that the lower bound is very close to the computed solution, thus providing a near optimal solution. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/3914814
- author
- Ulén, Johannes LU and Olsson, Carl LU
- organization
- publishing date
- 2013
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Lecture Notes in Computer Science Vol. 8081 (Energy Minimization Methods in Computer Vision and Pattern Recognition)
- editor
- Heyden, Anders ; Kahl, Fredrik ; Olsson, Carl ; Oskarsson, Magnus and Tai, Xue-Cheng
- volume
- 8081
- pages
- 14 pages
- publisher
- Springer
- conference name
- Energy Minimization Methods in Computer Vision and Pattern Recognition, 9th International Conference, EMMCVPR 2013 Lund, Sweden, August 19-21, 2013
- conference location
- Lund, Sweden
- conference dates
- 2013-08-19 - 2013-08-21
- external identifiers
-
- scopus:84884914361
- ISSN
- 1611-3349
- 0302-9743
- ISBN
- 978-3-642-40394-1 (print)
- 978-3-642-40395-8 (online)
- DOI
- 10.1007/978-3-642-40395-8_7
- language
- English
- LU publication?
- yes
- id
- 060f261a-9281-4434-9554-a06ce1403520 (old id 3914814)
- date added to LUP
- 2016-04-01 10:18:55
- date last changed
- 2024-08-11 18:59:51
@inproceedings{060f261a-9281-4434-9554-a06ce1403520,
abstract = {{Second derivative regularization methods for dense stereo matching is<br/><br>
a topic of intense research. Some of the most successful recent methods employ so called binary fusion moves where the combination of two proposal solutions is computed. In many cases the fusion move can be solved optimally, but the approach is limited to fusing pairs of proposals in each move. For multiple proposals iterative binary fusion may potentially lead to local minima.<br/><br>
In this paper we demonstrate how to simultaneously fuse more than two proposals at the same time for a 2nd order stereo regularizer. The optimization is made possible by effectively computing a generalized distance transform. This allows for computation of messages in linear time in the number of proposals. In addition the approach provides a lower bound on the globally optimal solution of the multi-fusion problem. We verify experimentally that the lower bound is very close to the computed solution, thus providing a near optimal solution.}},
author = {{Ulén, Johannes and Olsson, Carl}},
booktitle = {{Lecture Notes in Computer Science Vol. 8081 (Energy Minimization Methods in Computer Vision and Pattern Recognition)}},
editor = {{Heyden, Anders and Kahl, Fredrik and Olsson, Carl and Oskarsson, Magnus and Tai, Xue-Cheng}},
isbn = {{978-3-642-40394-1 (print)}},
issn = {{1611-3349}},
language = {{eng}},
pages = {{80--93}},
publisher = {{Springer}},
title = {{Simultaneous Fusion Moves for 3D-label Stereo}},
url = {{http://dx.doi.org/10.1007/978-3-642-40395-8_7}},
doi = {{10.1007/978-3-642-40395-8_7}},
volume = {{8081}},
year = {{2013}},
}