Disparity map estimation using image pyramid

The purpose of a short-baseline stereo matching algorithm is calculation of the disparity map for a given rectified
stereo pair. Most stereo algorithms presented in the literature achieve this goal by searching all possible disparities
for all pixels. This may be extremely costly if an image size and search range are large. In this paper we show that the use of a gaussian image pyramid can significantly reduce the number of disparities that have to be searched and thus offer a significantly speeds up the calculation process. In the same time the quality of the final disparity maps does is not much worse than the one obtained by the full-search algorithm. All tests are done for the local stereo algorithms.