JavaScript is disabled for your browser. Some features of this site may not work without it.
Computing Visual Correspondence with Occlusions via Graph Cuts

Author
Kolmogorov, Vladimir; Zabih, Ramin
Abstract
Several new algorithms for visual correspondence based on graph cuts 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 two new methods which properly address occlusions, while preserving the advantages of graph cut algorithms. We give experimental results for stereo as well as motion, which demonstrate that our methods perform well both at detecting occlusions and computing disparities.
Date Issued
2001-03-07Publisher
Cornell University
Subject
computer science; technical report
Previously Published As
http://techreports.library.cornell.edu:8081/Dienst/UI/1.0/Display/cul.cs/TR2001-1838
Type
technical report