Abstract

Motion segmentation can be addressed as a subspace cluster- ing problem, assuming that the tra jectories of interest points are known. However, establishing point correspondences is in itself a challenging task. Most existing approaches tackle the correspondence estimation and motion segmentation problems separately. In this paper, we introduce an approach to performing motion segmentation without any prior knowl- edge of point correspondences. We formulate this problem in terms of Partial Permutation Matrices (PPMs) and aim to match feature de- scriptors while simultaneously encouraging point tra jectories to satisfy subspace constraints. This lets us handle outliers in both point loca- tions and feature appearance. The resulting optimization problem can be solved via the Alternating Direction Method of Multipliers (ADMM), where each subproblem has an efficient solution. Our experimental evalu- ation on synthetic and real sequences clearly evidences the benefits of our formulation over the traditional sequential approach that first estimates correspondences and then performs motion segmentation.