Global stereo reconstruction under second-order smoothness priors

Second-order priors on the smoothness of 3D surfaces are a better model of typical scenes than first-order priors. However, stereo reconstruction using global inference algorithms, such as graph cuts, has not been able to incorporate second-order priors because the triple cliques needed to express t...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on pattern analysis and machine intelligence. - 1998. - 31(2009), 12 vom: 20. Dez., Seite 2115-28
Auteur principal: Woodford, Oliver (Auteur)
Autres auteurs: Torr, Philip, Reid, Ian, Fitzgibbon, Andrew
Format: Article en ligne
Langue:English
Publié: 2009
Accès à la collection:IEEE transactions on pattern analysis and machine intelligence
Sujets:Journal Article
LEADER 01000caa a22002652 4500
001 NLM192095366
003 DE-627
005 20250210214253.0
007 cr uuu---uuuuu
008 231223s2009 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2009.131  |2 doi 
028 5 2 |a pubmed25n0640.xml 
035 |a (DE-627)NLM192095366 
035 |a (NLM)19834135 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Woodford, Oliver  |e verfasserin  |4 aut 
245 1 0 |a Global stereo reconstruction under second-order smoothness priors 
264 1 |c 2009 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 01.02.2010 
500 |a Date Revised 16.10.2009 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Second-order priors on the smoothness of 3D surfaces are a better model of typical scenes than first-order priors. However, stereo reconstruction using global inference algorithms, such as graph cuts, has not been able to incorporate second-order priors because the triple cliques needed to express them yield intractable (nonsubmodular) optimization problems. This paper shows that inference with triple cliques can be effectively performed. Our optimization strategy is a development of recent extensions to alpha -- expansion, based on the "QPBO" algorithm. The strategy is to repeatedly merge proposal depth maps using a novel extension of QPBO. Proposal depth maps can come from any source, for example, frontoparallel planes as in alpha-expansion, or indeed any existing stereo algorithm, with arbitrary parameter settings 
650 4 |a Journal Article 
700 1 |a Torr, Philip  |e verfasserin  |4 aut 
700 1 |a Reid, Ian  |e verfasserin  |4 aut 
700 1 |a Fitzgibbon, Andrew  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1998  |g 31(2009), 12 vom: 20. Dez., Seite 2115-28  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:31  |g year:2009  |g number:12  |g day:20  |g month:12  |g pages:2115-28 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2009.131  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 31  |j 2009  |e 12  |b 20  |c 12  |h 2115-28