Abstract. Virtually all variational methods for motion estimation regularize the gradient of the flow field, which introduces a bias towards piecewise constant motions in weakly te...
Werner Trobin, Thomas Pock, Daniel Cremers, Horst ...
In this paper we present a model-based algorithm for the estimation of 3D motion and the analysis of facial expressions of a speaking person. A set of facial animation parameters ...
This paper proposes an hybrid approach to estimate the 3D pose of an object. The integration of texture information based on image intensities in a more classical non-linear edge-...
This paper demonstrates how a simple, yet effective, set of features enables to integrate ensemble classifiers in optical flow based tracking. In particular, gray value differences...
We present a new reliable hybrid recursive method for optical flow estimation. The method efficiently combines the advantage of discrete motion estimation and optical flow estimati...