Higher order energy functions have the ability to encode
high level structural dependencies between pixels, which
have been shown to be extremely powerful for image labeling
pro...
Carsten Rother (Microsoft Research Cambridge), Pus...
This paper addresses the problem of exactly inferring the maximum a posteriori solutions of discrete multi-label MRFs or CRFs with higher order cliques. We present a framework to ...
—In this paper, we present novel techniques that improve the computational and memory efficiency of algorithms for solving multi-label energy functions arising from discrete MRF...
Karteek Alahari, Pushmeet Kohli, Philip H. S. Torr
Markov random fields with higher order potentials have emerged as a powerful model for several problems in computer vision. In order to facilitate their use, we propose a new rep...
In this paper, we present novel techniques that improve the computational and memory efficiency of algorithms for solving multi-label energy functions arising from discrete MRFs o...
Karteek Alahari, Pushmeet Kohli, Philip H. S. Torr