Global stereo reconstruction under second order smoothness priors

Conference item

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 (non-submodular) optimization problems.
This paper shows that inference with triple cliques can be effectively optimized. Our optimization strategy is a development of recent extensions to α-expansion, based on the “QPBO” algorithm [5, 14, 26]. 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 fronto-parallel planes as in α-expansion, or indeed any existing stereo algorithm, with arbitrary parameter settings.
Experimental results demonstrate the usefulness of the second-order prior and the efficacy of our optimization framework. An implementation of our stereo framework is available online [34].

Authors: Woodford, OJ; Torr, PHS; Reid, ID; Fitzgibbon, AW

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IEEE
• Host title: 2008 IEEE Conference on Computer Vision and Pattern Recognition
• Pages: 1-8
• Publication date: 2008-08-05
• Acceptance date: 2007-12-03
• Event title: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008)
• Event location: Anchorage, Alaska
• Event start date: 2008-06-24
• Event end date: 2008-06-26
• DOI: 10.1109/cvpr.2008.4587672
• ISSN: 1063-6919
• EISBN: 9781424422432
• ISBN: 9781424422425
• Language: English