Fast stereo-matching using translation-invariant wavelet pyramid
Zsuzsanna Püspöki, BIG

Seminar • 30 August 2010 • BM 4.233

Abstract
We address the problem of disparity estimation from two-frame stereo images. We begin with a brief overview of the state-of-the-art stereo algorithms, particularly the ones based on graph optimization. With this class, we discuss dynamic programming in details. Graph-based algorithms tend to be rather slow when both the stereo-images and the disparities are large. We propose a "coarse-to-fine" algorithm that does narrow-band dynamic programming on wavelet pyramids to reduce the computation time for such images. The key feature of our pyramid is that it provides significant translation-invariance at the cost of moderate redundancy. We evaluate our algorithm on the benchmark Middlebury database [vision.middlebury.edu/stereo]. Finally, we present some experiment results to illustrate the advantages of the method.