Show simple item record

dc.contributor.authorSánchez-Riera, Jordi
dc.contributor.authorOstlund, Jonas
dc.contributor.authorFua, Pascal
dc.contributor.authorMoreno-Noguer, Francesc
dc.contributor.otherInstitut de Robòtica i Informàtica Industrial
dc.date.accessioned2010-11-23T18:49:10Z
dc.date.available2010-11-23T18:49:10Z
dc.date.created2010
dc.date.issued2010
dc.identifier.citationSánchez, J. [et al.]. Simultaneous pose, correspondence and non-rigid shape. A: IEEE Conference on Computer Vision and Pattern Recognition. "IEEE Conference on Computer Vision and Pattern Recognition(2010)". San Francisco: 2010, p. 1189-1196.
dc.identifier.urihttp://hdl.handle.net/2117/10384
dc.description.abstractRecent works have shown that 3D shape of non-rigid surfaces can be accurately retrieved from a single image given a set of 3D-to-2D correspondences between that image and another one for which the shape is known. However, existing approaches assume that such correspondences can be readily established, which is not necessarily true when large deformations produce significant appearance changes between the input and the reference images. Furthermore, it is either assumed that the pose of the camera is known, or the estimated solution is pose-ambiguous. In this paper we relax all these assumptions and, given a set of 3D and 2D unmatched points, we present an approach to simultaneously solve their correspondences, compute the camera pose and retrieve the shape of the surface in the input image. This is achieved by introducing weak priors on the pose and shape that we model as Gaussian Mixtures. By combining them into a Kalman filter we can progressively reduce the number of 2D candidates that can be potentially matched to each 3D point, while pose and shape are refined. This lets us to perform a complete and efficient exploration of the solution space and retain the best solution.
dc.format.extent8 p.
dc.language.isoeng
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Reconeixement de formes
dc.subject.lcshPattern recognition systems
dc.subject.othercomputer vision object detection PARAULES AUTOR: deformable surfaces
dc.subject.other3D reconstruction
dc.titleSimultaneous pose, correspondence and non-rigid shape
dc.typeConference report
dc.subject.lemacReconeixement de formes (Informàtica)
dc.contributor.groupUniversitat Politècnica de Catalunya. VIS - Visió Artificial i Sistemes Intel·ligents
dc.identifier.doi10.1109/CVPR.2010.5539831
dc.subject.inspecClassificació INSPEC::Pattern recognition::Object recognition
dc.relation.publisherversionhttp://dx.doi.org/10.1109/CVPR.2010.5539831
dc.rights.accessRestricted access - publisher's policy
drac.iddocument4128272
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/FP7/247947/EU/Gardening with a Cognitive System/GARNICS
upcommons.citation.authorSánchez, J.; Ostlund, J.; Fua, P.; Moreno, F.
upcommons.citation.contributorIEEE Conference on Computer Vision and Pattern Recognition
upcommons.citation.pubplaceSan Francisco
upcommons.citation.publishedtrue
upcommons.citation.publicationNameIEEE Conference on Computer Vision and Pattern Recognition(2010)
upcommons.citation.startingPage1189
upcommons.citation.endingPage1196


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Except where otherwise noted, content on this work is licensed under a Creative Commons license: Attribution-NonCommercial-NoDerivs 3.0 Spain