A Volumetric Iterative Approach to Stereo Matching and Occlusion Detection

This paper presents a stereo algorithm for obtaining disparity maps with explicitly detected occlusion. To produce smooth and detailed disparity maps, two assumptions that were originally proposed by Marr and Poggio are adopted: uniqueness and continuity. That is, the disparity maps have unique values and are continuous almost everywhere. A volumetric approach is taken to utilize these assumptions. A 3D array of match likelihood values is constructed with each value corresponding to a pixel in an image and a disparity relative to another image. An iterative algorithm updates the match likelihood values by diffusing support among neighboring values and inhibiting others. After the values have converged, the region of occlusion is explicitly detected. To demonstrate the effectiveness of the algorithm we present the processing results from synthetic and real image pairs, with comparison to results by other methods. The resulting disparity maps are smooth and detailed with occlusions detected. Disparity values in areas of repetitive texture are also found correctly.