Stereo matching using belief propagation

TLDR

The stereo Markov network models depth, discontinuity, and occlusion using three coupled Markov random fields. The paper formulates stereo matching as a Markov network and solves it with Bayesian belief propagation. The method eliminates line and binary processes with robust functions, then applies belief propagation for MAP estimation, and can incorporate low‑level cues for improved results. Experiments show the method performs comparably to state‑of‑the‑art stereo algorithms on many test cases.

Abstract

In this paper, we formulate the stereo matching problem as a Markov network and solve it using Bayesian belief propagation. The stereo Markov network consists of three coupled Markov random fields that model the following: a smooth field for depth/disparity, a line process for depth discontinuity, and a binary process for occlusion. After eliminating the line process and the binary process by introducing two robust functions, we apply the belief propagation algorithm to obtain the maximum a posteriori (MAP) estimation in the Markov network. Other low-level visual cues (e.g., image segmentation) can also be easily incorporated in our stereo model to obtain better stereo results. Experiments demonstrate that our methods are comparable to the state-of-the-art stereo algorithms for many test cases.