Segmentation-based dense stereo matching algorithm for virtual view synthesis

This paper presents a new stereo matching algorithm to compute dense disparity map for virtual view synthesis. The reference view is segmented using mean-shift segmentation method. An adaptive support-weights window-based approach is adopted to obtain the initial disparity map per pixel. We utilize cross-checking technique to filter out reliable correspondences and detect occlusion regions. The disparity in each segment is represented as a 3D planar plane by a robust plane fitting process. With the plane model of each segment, the disparity of unreliable points and occlusion regions can be refined. Finally, pixel domain matches are defined by computed disparity map, and virtual view can be synthesized by interpolating. Experimental results with the Middlebury stereo testing images show that our stereo matching algorithm gives a good performance.