Show simple item record

dc.contributor.authorBoykov, Yurien_US
dc.contributor.authorVeksler, Olgaen_US
dc.contributor.authorZabih, Raminen_US
dc.date.accessioned2007-04-23T18:11:29Z
dc.date.available2007-04-23T18:11:29Z
dc.date.issued1997-12en_US
dc.identifier.citationhttp://techreports.library.cornell.edu:8081/Dienst/UI/1.0/Display/cul.cs/TR97-1658en_US
dc.identifier.urihttps://hdl.handle.net/1813/7312
dc.description.abstractMarkov Random Fields (MRF's) can be used for a wide variety of vision problems. In this paper we address the estimation of first-order MRF's with a particular clique potential that resembles a well. We show that the maximum {\em a posteriori} estimate of such an MRF can be obtained by solving a multiway cut problem on a graph. This allows the application of near linear-time algorithms for computing provably good approximations. We formulate the visual correspondence problem as an MRF in our framework, and show that this yields quite promising results on real data with ground truth.en_US
dc.format.extent316102 bytes
dc.format.extent1925663 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.titleMarkov Random Fields with Efficient Approximationsen_US
dc.typetechnical reporten_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Statistics