ML Anthology

A Symmetric Patch-Based Correspondence Model for Occlusion Handling

Yi Deng, Qiong Yang, Xueyin Lin, Xiaoou Tang
ICCV 2005 pp. 1316-1322
doi:10.1109/ICCV.2005.23 /iccv/2005/deng2005iccv-symmetric/

Abstract

Occlusion is one of the challenging problems in stereo. In this paper, we solve the problem in a segment-based style. Both images are segmented, and we propose a novel patch-based stereo algorithm that cuts the segments of one image using the segments of the other, and handles occlusion areas in a proper way. A symmetric graph-cuts optimization framework is used to find correspondence and occlusions simultaneously. The experimental results show superior performance of the proposed algorithm, especially on occlusions, untextured areas and discontinuities

PDF ICCV Semantic Scholar

Cite

Text

Deng et al. "A Symmetric Patch-Based Correspondence Model for Occlusion Handling." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.23

Markdown

[Deng et al. "A Symmetric Patch-Based Correspondence Model for Occlusion Handling." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/deng2005iccv-symmetric/) doi:10.1109/ICCV.2005.23

BibTeX

@inproceedings{deng2005iccv-symmetric,
  title     = {{A Symmetric Patch-Based Correspondence Model for Occlusion Handling}},
  author    = {Deng, Yi and Yang, Qiong and Lin, Xueyin and Tang, Xiaoou},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2005},
  pages     = {1316-1322},
  doi       = {10.1109/ICCV.2005.23},
  url       = {https://mlanthology.org/iccv/2005/deng2005iccv-symmetric/}
}