File Download
Supplementary

Conference Paper: Using illumination estimated from silhouettes to carve surface details on visual hull

TitleUsing illumination estimated from silhouettes to carve surface details on visual hull
Authors
Issue Date2008
PublisherBritish Machine Vision Association.
Citation
The British Machine Vision Conference (BMVC) 2008, Leeds, U.K., 1-4 September 2008. In Proceedings of the British Machine Vision Conference, 2008, v. 2, p. 895-904 How to Cite?
AbstractThis paper deals with the problems of scene illumination estimation and shape recovery from an image sequence of a smooth textureless object. A novel method that exploits the surface points estimated from the silhouettes for recovering the scene illumination is introduced. Those surface points are acquired by a dual space approach and filtered according to their rank errors. Selected surface points allow a direct closed-form solution of illumination. In the mesh evolution step, an algorithm for optimizing the visual hull mesh is developed. It evolves the mesh by iteratively estimating both the surface normal and depth that maximize the photometric consistency across the sequence. Compared with previous work which optimizes the mesh by estimating the surface normal only, the proposed method shows better convergence and can recover better surface details, especially when concavities are deep and sharp.
Persistent Identifierhttp://hdl.handle.net/10722/137149

 

DC FieldValueLanguage
dc.contributor.authorLi, S-
dc.contributor.authorWong, KKY-
dc.contributor.authorSchnieders, D-
dc.date.accessioned2011-08-24T06:43:00Z-
dc.date.available2011-08-24T06:43:00Z-
dc.date.issued2008-
dc.identifier.citationThe British Machine Vision Conference (BMVC) 2008, Leeds, U.K., 1-4 September 2008. In Proceedings of the British Machine Vision Conference, 2008, v. 2, p. 895-904-
dc.identifier.urihttp://hdl.handle.net/10722/137149-
dc.description.abstractThis paper deals with the problems of scene illumination estimation and shape recovery from an image sequence of a smooth textureless object. A novel method that exploits the surface points estimated from the silhouettes for recovering the scene illumination is introduced. Those surface points are acquired by a dual space approach and filtered according to their rank errors. Selected surface points allow a direct closed-form solution of illumination. In the mesh evolution step, an algorithm for optimizing the visual hull mesh is developed. It evolves the mesh by iteratively estimating both the surface normal and depth that maximize the photometric consistency across the sequence. Compared with previous work which optimizes the mesh by estimating the surface normal only, the proposed method shows better convergence and can recover better surface details, especially when concavities are deep and sharp.-
dc.languageeng-
dc.publisherBritish Machine Vision Association.-
dc.relation.ispartofProceedings of the British Machine Vision Conference-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.titleUsing illumination estimated from silhouettes to carve surface details on visual hullen_US
dc.typeConference_Paperen_US
dc.identifier.emailLi, S: sdli@cs.hku.hk-
dc.identifier.emailWong, KKY: kykwong@cs.hku.hk-
dc.identifier.emailSchnieders, D: sdirk@cs.hku.hk-
dc.description.naturepostprint-
dc.identifier.hkuros148739-
dc.identifier.volume2-
dc.identifier.spage895-
dc.identifier.epage904-
dc.description.otherThe British Machine Vision Conference (BMVC) 2008, Leeds, U.K., 1-4 September 2008. In Proceedings of the British Machine Vision Conference, 2008, v. 2, p. 895-904-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats