On partial optimality in multi-label MRFs
We consider the problem of optimizing multilabel MRFs, which is in general NP-hard and ubiquitous in low-level computer vision. One approach for its solution is to formulate it as an integer linear programming and relax the integrality constraints. The approach we consider in this paper is to first...
Auteurs principaux: | Kohli, P, Shekhovtsov, A, Rother, C, Kolmogorov, V, Torr, P |
---|---|
Format: | Conference item |
Langue: | English |
Publié: |
Association for Computing Machinery
2008
|
Documents similaires
-
Reduce, reuse and recycle: efficiently solving multi-label MRFs
par: Alahari, K, et autres
Publié: (2008) -
An analysis of convex relaxations for MAP estimation of discrete MRFs
par: Pawan Kumar, M, et autres
Publié: (2009) -
Dynamic hybrid algorithms for MAP inference in discrete MRFs
par: Alahari, K, et autres
Publié: (2009) -
A tiered move-making algorithm for general pairwise MRFs
par: Vineet, V, et autres
Publié: (2012) -
Integrating vision modules with coupled MRFs
par: Poggio, Tomaso
Publié: (2008)