Show simple item record

dc.contributor.convenorRoberto Cipolla, Roberto Colombo, Alberto Del Bimboen_US
dc.contributor.authorZhang, Paulen_US
dc.contributor.authorGao, Yongshengen_US
dc.contributor.authorCaelli, Terrenceen_US
dc.contributor.editorAndrew Fitzgibbon, Svetlana Lazebnik, Pietro Perona, Yoichi Sato, et alen_US
dc.date.accessioned2017-05-03T14:13:06Z
dc.date.available2017-05-03T14:13:06Z
dc.date.issued2012en_US
dc.date.modified2013-07-08T05:09:33Z
dc.identifier.refurihttp://eccv2012.unifi.it/en_US
dc.identifier.doi10.1007/978-3-642-33715-4_14en_US
dc.identifier.urihttp://hdl.handle.net/10072/52334
dc.description.abstractThe appearance of a 3D object depends on both the viewing directions and illumination conditions. It is proven that all n-pixel images of a convex object with Lambertian surface under variable lighting from infinity form a convex polyhedral cone (called illumination cone) in n-dimensional space. This paper tries to answer the other half of the question: What is the set of images of an object under all viewing directions? A novel image representation is proposed, which transforms any n-pixel image of a 3D object to a vector in a 2n-dimensional pose space. In such a pose space, we prove that the transformed images of a 3D object under all viewing directions form a parametric manifold in a 6-dimensional linear subspace. With in-depth rotations along a single axis in particular, this manifold is an ellipse. Furthermore, we show that this parametric pose manifold of a convex object can be estimated from a few images in different poses and used to predict object's appearances under unseen viewing directions. These results immediately suggest a number of approaches to object recognition, scene detection, and 3D modelling. Experiments on both synthetic data and real images were reported, which demonstrates the validity of the proposed representation.en_US
dc.description.peerreviewedYesen_US
dc.description.publicationstatusYesen_US
dc.languageEnglishen_US
dc.publisherSpringeren_US
dc.publisher.placeGermanyen_US
dc.publisher.urihttp://eccv2012.unifi.it/en_US
dc.relation.ispartofstudentpublicationNen_US
dc.relation.ispartofconferencename12th European Conference on Computer Vision (ECCV)en_US
dc.relation.ispartofconferencetitleComputer Vision – ECCV 2012. 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part Ven_US
dc.relation.ispartofdatefrom2012-10-07en_US
dc.relation.ispartofdateto2012-10-13en_US
dc.relation.ispartoflocationFlorence, Italyen_US
dc.rights.retentionYen_US
dc.subject.fieldofresearchComputer Visionen_US
dc.subject.fieldofresearchcode080104en_US
dc.titleParametric Manifold of an Object under Different Viewing Directionsen_US
dc.typeConference outputen_US
dc.type.descriptionE1 - Conference Publications (HERDC)en_US
dc.type.codeE - Conference Publicationsen_US
gro.facultyGriffith Sciences, Griffith School of Engineeringen_US
gro.date.issued2012
gro.hasfulltextNo Full Text


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record