Issue No. 12 - December (2009 vol. 31)
Oliver Woodford , University of Oxford, Oxford
Philip Torr , Oxford Brookes University, Oxford
Ian Reid , University of Oxford, Oxford
Andrew Fitzgibbon , Microsoft Research Ltd., Cambridge
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.
Stereo, second-order prior, discrete optimization, graph cuts.
P. Torr, A. Fitzgibbon, O. Woodford and I. Reid, "Global Stereo Reconstruction under Second-Order Smoothness Priors," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 31, no. , pp. 2115-2128, 2009.