Acyclic belief propagation for stereo matching

Most of the works for solving early vision problems, such as stereo, rely on inference techniques and cyclic graphical models. Although Loopy Belief Propagation is one of the most interesting tools as it applies to that research field, loops are still a major challenge to face: the main problem arising with them is the introduction of approximation issues which could affect the accuracy of the final results. Therefore, breaking loops could be the winning strategy to overcome these problems. In this paper, we describe a way to consider an MRF grid as composed by a suitable set of singly connected graphs. Then, an acyclic propagation scheme, based on that set, is given accordingly. Experiments performed on different stereo pairs will prove that our approach is up to the current state-of-art and it spreads several new research issues for the future.