Simultaneous Fusion Moves for 3D-label Stereo
Author
Editor
- Anders Heyden
- Fredrik Kahl
- Carl Olsson
- Magnus Oskarsson
- Xue-Cheng Tai
Summary, in English
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.
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.
Department/s
Publishing year
2013
Language
English
Pages
80-93
Publication/Series
Lecture Notes in Computer Science Vol. 8081 (Energy Minimization Methods in Computer Vision and Pattern Recognition)
Volume
8081
Document type
Conference paper
Publisher
Springer
Topic
- Computer Vision and Robotics (Autonomous Systems)
- Mathematics
Conference name
Energy Minimization Methods in Computer Vision and Pattern Recognition, 9th International Conference, EMMCVPR 2013 Lund, Sweden, August 19-21, 2013
Conference date
2013-08-19 - 2013-08-21
Conference place
Lund, Sweden
Status
Published
Research group
- Mathematical Imaging Group
ISBN/ISSN/Other
- ISSN: 0302-9743
- ISSN: 1611-3349
- ISBN: 978-3-642-40394-1 (print)
- ISBN: 978-3-642-40395-8 (online)