Stereo Matching based on Global Edge Constraint and Variable Window Propagation

In this paper, we address the problem of stereo matching. Edge information is sufficiently explored in our algorithm to compose the Global Edge Constraint (GEC). By using the GEC, an optimal correlation window for each specific match (i.e. seed match) can be estimated and pixels within the window would be quickly matched with propagation. We evaluate our algorithm with real stereo pairs and both high accuracy disparity maps and a handling of occlusions can be achieved. Experimental results show the good performance of the proposed GEC in stereo matching.