A comparison of multi-resolution stereo matching methods

This paper implements four interpolation methods to modify the adaptive support weight (ASW) algorithm in multiresolution image representation. The disparity values at lower resolution level are used to determine disparity values of undetermined pixels at higher level during the interpolation procedure. The first interpolation method fills an undetermined pixel (a gap) with the averaged disparities of neighboring pixels. The second method examines the degree of color similarity between neighboring pixels. The similarity is used in neighboring disparity interpolation. The third method computes the disparity of the gap with ASW. The last method computes the disparity of the gap by considering minimum and maximum disparity values of neighboring pixels.