Stereo Matching by Joint Energy Minimization

In [7], Mozerov et al. propose to perform stereo matching as a twostep energy minimization problem. They formulate cost filtering as a local energy minimization model, and solve the fully connected MRF model and the locally connected MRF model sequentially. In this paper we intend to combine the two steps of energy minimization in order to improve stereo matching results. We propose to jointly solve the fully connected and locally connected models, taking both their advantages into account. The joint model is solved by mean field approximations and the experiments show that the locally connected potential makes up for the loss caused by fast approximations. While remaining efficient, our joint model outperforms the two-step energy minimization approach on the Middlebury stereo benchmark.