Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 31, Issue 12, Pages 2115-2128Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2009.131
Keywords
Stereo; second-order prior; discrete optimization; graph cuts
Funding
- EPSRC [EP/C007220/1, EP/C006631/1]
- Royal Society Wolfson Merit Award
- Engineering and Physical Sciences Research Council [EP/C006631/1] Funding Source: researchfish
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available