DMCA
Symmetric stereo matching for occlusion handling (2005)
Cached
Download Links
- [research.microsoft.com]
- [research.microsoft.com]
- [research.microsoft.com]
- [research.microsoft.com]
- [research.microsoft.com]
- [research.microsoft.com]
- DBLP
Other Repositories/Bibliography
| Venue: | IEEE Conf. on Computer Vision and Pattern Recognition (CVPR |
| Citations: | 133 - 4 self |
BibTeX
@INPROCEEDINGS{Sun05symmetricstereo,
author = {Jian Sun and Yin Li and Sing Bing and Kang Heung-yeung Shum},
title = {Symmetric stereo matching for occlusion handling},
booktitle = {IEEE Conf. on Computer Vision and Pattern Recognition (CVPR},
year = {2005},
pages = {399--406}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper, we propose a symmetric stereo model to han-dle occlusion in dense two-frame stereo. Our occlusion reasoning is directly based on the visibility constraint that is more general than both ordering and uniqueness con-straints used in previous work. The visibility constraint requires occlusion in one image and disparity in the other to be consistent. We embed the visibility constraint within an energy minimization framework, resulting in a symmet-ric stereo model that treats left and right images equally. An iterative optimization algorithm is used to approximate the minimum of the energy using belief propagation. Our stereo model can also incorporate segmentation as a soft constraint. Experimental results on the Middlebury stereo images show that our algorithm is state-of-the-art. 1
Keyphrases
occlusion handling symmetric stereo visibility constraint symmet-ric stereo model previous work uniqueness con-straints stereo model iterative optimization algorithm symmetric stereo model belief propagation occlusion reasoning soft constraint right image energy minimization framework middlebury stereo image experimental result han-dle occlusion dense two-frame stereo
