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 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.
Computing visual correspondence with occlusions using graph cuts
Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 ; 2 ; 508-515 vol.2
01.01.2001
1138759 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Computing Visual Correspondence with Occlusions via Graph Cuts
British Library Conference Proceedings | 2001
|Extracting Dense Features for Visual Correspondence with Graph Cuts
British Library Conference Proceedings | 2003
|Computing Geodesics and Minimal Surfaces via Graph Cuts
British Library Conference Proceedings | 2003
|Computing geodesics and minimal surfaces via graph cuts
IEEE | 2003
|