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 ...
We propose a novel MRF-based model for deformable image matching (also known as registration). The deformation is described by a field of discrete variables, representing displace...
We consider the problem of sequential decision making for random fields corrupted by noise. In this scenario, the decision maker observes a noisy version of the data, yet judged wi...
The notion of using context information for solving highlevel vision problems has been increasingly realized in the field. However, how to learn an effective and efficient context...
In this paper we explore a multiple hypothesis approach to estimating rigid motion from a moving stereo rig. More precisely, we introduce the use of Gaussian mixtures to model cor...