Abstract

Dense optical flow estimation in images is a challenging prob- lem because the algorithm must coordinate the estimated motion across large regions in the image, while avoiding inappropriate smoothing over motion boundaries. Recent works have advocated for the use of nonlo- cal regularization to model long-range correlations in the flow. However, incorporating nonlocal regularization into an energy optimization frame- work is challenging due to the large number of pairwise penalty terms. Existing techniques either substitute intermediate filtering of the flow field for direct optimization of the nonlocal ob jective, or suffer substan- tial performance penalties when the range of the regularizer increases. In this paper, we describe an optimization algorithm that efficiently han- dles a general type of nonlocal regularization ob jectives for optical flow estimation. The computational complexity of the algorithm is indepen- dent of the range of the regularizer. We show that nonlocal regularization improves estimation accuracy at longer ranges than previously reported, and is complementary to intermediate filtering of the flow field. Our al- gorithm is simple and is compatible with many optical flow models.