Abstract
This paper proposes modeling motion in a bilateral domain that aug- ments spatial information with the motion itself. We use the bilateral domain to reformulate a piecewise smooth constraint as continuous global modeling con- straint. The resultant model can be robustly computed from highly noisy scattered feature points using a global minimization. We demonstrate how the model can reliably obtain large numbers of good quality correspondences over wide base- lines, while keeping outliers to a minimum.