Dense Stereo Correspondence with Contrast Context Histogram, Segmentation-Based Two-Pass Aggregation and Occlusion Handling.

In a local and perceptual organization framework, a novel stereo correspondence algorithm is proposed to provide dense and accurate disparity maps under point ambiguity. First, the initial matching technique is based on raw matching cost obtained from local descriptor with contrast context histogram and two-pass cost aggregation via segmentation-based adaptive support weight. Second, the disparity estimation procedure consists sequentially of two steps: namely, a narrow occlusion handling and a multi-directional weighted least square (WLS) fitting for large occlusion. The experiment results indicate that our algorithm can increase robustness against outliers, and then obtain comparable and accurate disparity than other local stereo methods effectively, and it is even better than some algorithms using advanced and offline but computationally complicated global optimization based algorithms. [ABSTRACT FROM AUTHOR]