Optical Flow Estimation Using Discontinuity Conforming Filters

The discontinuities and the large image displacements pose some of the hardest problems in flow estimation. This paper uses a set of filters that change shape to avoid blending of the constraints across discontinuity boundaries. This is done by using an incompatibility measure of the constraints of neighbouring pixels. The algorithm is embedded in a coarse to fine multigrid scheme to address the problem of large displacements. We report results on real images which show that the algorithm works very well.