ML Anthology

Computing Visual Correspondence with Occlusions via Graph Cuts

Vladimir Kolmogorov, Ramin Zabih
ICCV 2001 pp. 508-515
doi:10.1109/ICCV.2001.937668 /iccv/2001/kolmogorov2001iccv-computing/

Abstract

Several new algorithms for visual correspondence based on graph cuts [7, 14, 17] have recently been developed. While these methods give very strong results in practice, they do not handle occlusions properly. Specifically, they treat the two input images asymmetrically, and they do not ensure that a pixel corresponds to at most one pixel in the other image. In this paper, we present a new method which properly addresses occlusions, while preserving the advantages of graph cut algorithms. We give experimental results for stereo as well as motion, which demonstrate that our method performs well both at detecting occlusions and computing disparities.

PDF ICCV Semantic Scholar

Cite

Text

Kolmogorov and Zabih. "Computing Visual Correspondence with Occlusions via Graph Cuts." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.937668

Markdown

[Kolmogorov and Zabih. "Computing Visual Correspondence with Occlusions via Graph Cuts." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/kolmogorov2001iccv-computing/) doi:10.1109/ICCV.2001.937668

BibTeX

@inproceedings{kolmogorov2001iccv-computing,
  title     = {{Computing Visual Correspondence with Occlusions via Graph Cuts}},
  author    = {Kolmogorov, Vladimir and Zabih, Ramin},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2001},
  pages     = {508-515},
  doi       = {10.1109/ICCV.2001.937668},
  url       = {https://mlanthology.org/iccv/2001/kolmogorov2001iccv-computing/}
}