Sciweavers

5 search results - page 1 / 1
» Minimizing Sparse Higher Order Energy Functions of Discrete ...
Sort
View
CVPR
2009
IEEE
14 years 11 months ago
Minimizing Sparse Higher Order Energy Functions of Discrete Variables
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...
CVPR
2008
IEEE
14 years 6 months ago
Exact inference in multi-label CRFs with higher order cliques
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 ...
Srikumar Ramalingam, Pushmeet Kohli, Karteek Alaha...
PAMI
2010
168views more  PAMI 2010»
13 years 2 months ago
Dynamic Hybrid Algorithms for MAP Inference in Discrete MRFs
—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
CVPR
2010
IEEE
14 years 20 days ago
Energy Minimization for Linear Envelope MRFs
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...
Pushmeet Kohli, M. Pawan Kumar
CVPR
2008
IEEE
14 years 6 months ago
Reduce, reuse & recycle: Efficiently solving multi-label MRFs
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