Show simple item record

dc.contributor.authorJin, Hailinen_US
dc.contributor.authorWang, Dejunen_US
dc.contributor.authorCremers, Danielen_US
dc.contributor.authorPrados, Emmanuelen_US
dc.contributor.authorYezzi, Anthonyen_US
dc.contributor.authorSoatto, Stefanoen_US
dc.date.accessioned2013-09-04T20:36:49Z
dc.date.available2013-09-04T20:36:49Z
dc.date.issued2008-03
dc.identifier.citationA. Duci, A. Yezzi, S. Mitter, and S. Soatto, “Region matching with missing parts,” In A. Heyden et al. (Eds.), ECCV 2002 7th European Conference on Computer Vision, Copenhagen, Denmark, May 28–31, 2002: proceedings, LNCS 2352, 48–62, 2002. Berlin ; New York: Springer.en_US
dc.identifier.issn0920-5691
dc.identifier.issn1573-1405
dc.identifier.urihttp://hdl.handle.net/1853/48787
dc.description©2008 Springer Science+Business Media. The original publication is available at www.springerlink.comen_US
dc.descriptionDOI: 10.1007/s11263-007-0055-yen_US
dc.description.abstractWe propose a variational algorithm to jointly estimate the shape, albedo, and light configuration of a Lambertian scene from a collection of images taken from different vantage points. Our work can be thought of as extending classical multi-view stereo to cases where point correspondence cannot be established, or extending classical shape from shading to the case of multiple views with unknown light sources. We show that a first naive formalization of this problem yields algorithms that are numerically unstable, no matter how close the initialization is to the true geometry. We then propose a computational scheme to overcome this problem, resulting in provably stable algorithms that converge to (local) minima of the cost functional. We develop a new model that explicitly enforces positivity in the light sources with the assumption that the object is Lambertian and its albedo is piecewise constant and show that the new model significantly improves the accuracy and robustness relative to existing approaches.en_US
dc.language.isoen_USen_US
dc.publisherGeorgia Institute of Technologyen_US
dc.subjectStereoscopic segmentationen_US
dc.subjectShape from shadingen_US
dc.subjectMulti-view stereoen_US
dc.subjectVariational 3Den_US
dc.subjectReconstructionen_US
dc.subjectLevel set methodsen_US
dc.subjectLighting and appearance reconstructionen_US
dc.title3-D Reconstruction of Shaded Objects from Multiple Images Under Unknown Illuminationen_US
dc.typeProceedingsen_US
dc.typePost-printen_US
dc.contributor.corporatenameAdobe Systems. Office of Technologyen_US
dc.contributor.corporatenameUniversität Bonnen_US
dc.contributor.corporatenameInstitut national de recherche en informatique et en automatique (France)en_US
dc.contributor.corporatenameGeorgia Institute of Technology. School of Electrical and Computer Engineeringen_US
dc.contributor.corporatenameUniversity of California, Los Angeles. Computer Science Dept.en_US
dc.publisher.originalSpringer Verlagen_US
dc.identifier.doi10.1007/s11263-007-0055-y


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record