A Course to Fine Multiscale Approach for Linear Least Squares Optical Flow Estimation

Tensor-based approaches for optical flow have been often criticized because of their limitations in handling large motions. This paper shows how to adapt them in a multiscale coarse-to-fine strategy. We show how the same ideas used in the variational framework can be adapted by working with both a multiscale image sequence as well as a multiscale, motion compensated tensor field. Several experiments are presented in order to compare it to some recent well known multiscale techniques. We demonstrate how this approach offers a good compromise between precision and computational efficiency.