Data-Driven Motion Estimation with Spatial Adaptation

Besides being an ill-posed problem, the pel-recursive computation of 2-D optical flow raises awealth of issues, such as the treatment of outliers, motion discontinuities and occlusion. Ourproposed approach deals with these issues within a common framework. It relies on the use of adata-driven technique called Generalized Cross Validation (GCV) to estimate the bestregularization scheme for a given moving pixel. In our model, a regularization matrix carriesinformation about different sources of error in its entries and motion vector estimation takes intoconsideration local image properties following a spatially adaptive. Preliminary experimentsindicate that this approach provides robust estimates of the optical flow.