Show simple item record

dc.contributor.authorZiegler, Remo
dc.contributor.authorMatusik, Wojciech
dc.contributor.authorPfister, Hanspeter
dc.contributor.authorMcMillan, Leonard
dc.date.accessioned2010-06-16T13:57:32Z
dc.date.issued2003
dc.identifier.citationZiegler, Remo, Wojciech Matusik, Hanspeter Pfister, and Leonard McMillan. 2003. 3D reconstruction using labeled image regions. In Proceedings Symposium on Geometry Processing: June 23-25, 2003, Aachen, Germany, ed. S. Spencer, L. Kobbelt, P. Schröder, and H. Hoppe, 248-259. Aire-la-Ville, Switzerland: Eurographics Association.en_US
dc.identifier.isbn1-58113-687-0en_US
dc.identifier.isbn3-905673-06-1en_US
dc.identifier.issn1727-8384en_US
dc.identifier.urihttp://nrs.harvard.edu/urn-3:HUL.InstRepos:4238984
dc.description.abstractIn this paper we present a novel algorithm for reconstructing 3D scenes from a set of images. The user defines a set of polygonal regions with corresponding labels in each image using familiar 2D photo-editing tools. Our reconstruction algorithm computes the 3D model with maximum volume that is consistent with the set of regions in the input images. The algorithm is fast, uses only 2D intersection operations, and directly computes a polygonal model. We implemented a user-assisted system for 3D scene reconstruction and show results on scenes that are difficult or impossible to reconstruct with other methods.en_US
dc.description.sponsorshipEngineering and Applied Sciencesen_US
dc.language.isoen_USen_US
dc.publisherEurographics Associationen_US
dc.relation.isversionofhttp://www.eg.org/en_US
dc.relation.hasversionhttp://gvi.seas.harvard.edu/sites/all/files/SGP2003_0.pdfen_US
dash.licenseLAA
dc.title3D Reconstruction Using Labeled Image Regionsen_US
dc.typeMonograph or Booken_US
dc.description.versionAccepted Manuscripten_US
dash.depositing.authorPfister, Hanspeter
dc.date.available2010-06-16T13:57:32Z
dash.contributor.affiliatedPfister, Hanspeter


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record