Show simple item record

dc.contributor.authorKolmogorov, Vladimiren_US
dc.contributor.authorZabih, Raminen_US
dc.date.accessioned2007-04-09T19:56:00Z
dc.date.available2007-04-09T19:56:00Z
dc.date.issued2001-03-07en_US
dc.identifier.citationhttp://techreports.library.cornell.edu:8081/Dienst/UI/1.0/Display/cul.cs/TR2001-1838en_US
dc.identifier.urihttps://hdl.handle.net/1813/5825
dc.description.abstractSeveral 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.en_US
dc.format.extent603878 bytes
dc.format.extent11060524 bytes
dc.format.mimetypeapplication/pdf
dc.format.mimetypeapplication/postscript
dc.language.isoen_USen_US
dc.publisherCornell Universityen_US
dc.subjectcomputer scienceen_US
dc.subjecttechnical reporten_US
dc.titleComputing Visual Correspondence with Occlusions via Graph Cutsen_US
dc.typetechnical reporten_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Statistics