Accurate and high density estimation of optical flow vectors in an image sequence is accomplished by a method that estimates the velocity distribution function for small overlappi...
Abstract. We use a simple yet powerful higher-order conditional random field (CRF) to model optical flow. It consists of a standard photoconsistency cost and a prior on affine mo...
An algorithm for optical ow estimation is presented for the case of discrete-time motion of an uncalibrated camera through a rigid world. Unlike traditional optical ow approaches t...
Jeffrey Mendelsohn, Eero P. Simoncelli, Ruzena Baj...
We propose in this paper a robust multi-resolution technique to estimate dense velocity field from image sequences. It couples a Gaussian pyramidal down-sampling decomposition to...
This paper suggests using discrete feature displacements and optical flow simultaneously to determine the camera motion and its velocity. This is advantageous when the number of ...