Establishing Visual Correspondence from Multi-Resolution Graph Cuts for Stereo-Motion

This paper presents the design and implementation of a multi-resolution graph cuts (MRGC) for stereo-motion framework that produces dense disparity maps. Both stereo and motion are estimated simultaneously under the origi- nal graph cuts framework [7]. Our framework extends the problem from one to five dimensions, creating a large in- crease in complexity. Using three different multi-resolution graph cut algorithms, LDNR, EL and SAC, we reduce the number of pixelsmand the number of labels n that limit the á . â swap algorithm (with complexity O(mn2) required from the definition of our semi-metric smoothness function. This results in a reduction of computation time and the abil- ity to handle larger images and larger label sets. The choice of the three MRGC algorithms to use in computation deter- mines the appropriate level of accuracy and computation time desired.