Stereo Reconstruction using High Order Likelihood

Under the popular Bayesian approach, a stereo problem can be formulated by defining likelihood and prior. Likeli-hoods are often associated with unary terms and priors are defined by pair-wise or higher order cliques in Markov ran-dom field (MRF). In this paper, we propose to use high order likelihood model in stereo. Numerous conventional patch based matching methods such as normalized cross correla-tion, Laplacian of Gaussian, or census filters are designed under the naive assumption that all the pixels of a patch have the same disparities. However, patch-wise cost can be formulated as higher order cliques for MRF so that the matching cost is a function of image patch’s disparities. A patch obtained from the projected image by a disparity map should provide a better match without the blurring effect around disparity discontinuities. Among patch-wise high order matching costs, the census filter approach can be eas-ily reduced to pair-wise cliques. The experimental results on census filter-based high order likelihood demonstrate the advantages of high order likelihood over independent iden-tically distributed unary model. 1