Estimation and segmentation of a dense disparity map for 3D reconstruction

This paper presents a new algorithm of disparity map segmentation in planar facets. Originalities of this method lies in the process of dense disparity map estimation, using the dynamic programming subject to interest points previously extracted. The segmentation of this map uses the normal vector at each pixel surface. The matching of pixels between the two images by dynamic programming provides us with a scattered disparity map. So the densification of this map is achieved by matching contour points extracted between the two available images. Experiments with real images have validated our method and have clearly shown the improvement over the existing methods. The dense disparity map obtained is reliable when compared to classical methods. We also get a normal vector map segmented in contours and in homogeneous regions reflecting 3D planar facets.