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...
Hoofdauteurs: | Kohli, P, Shekhovtsov, A, Rother, C, Kolmogorov, V, Torr, P |
---|---|
Formaat: | Conference item |
Taal: | English |
Gepubliceerd in: |
Association for Computing Machinery
2008
|
Gelijkaardige items
-
Reduce, reuse and recycle: efficiently solving multi-label MRFs
door: Alahari, K, et al.
Gepubliceerd in: (2008) -
An analysis of convex relaxations for MAP estimation of discrete MRFs
door: Pawan Kumar, M, et al.
Gepubliceerd in: (2009) -
Dynamic hybrid algorithms for MAP inference in discrete MRFs
door: Alahari, K, et al.
Gepubliceerd in: (2009) -
A tiered move-making algorithm for general pairwise MRFs
door: Vineet, V, et al.
Gepubliceerd in: (2012) -
Integrating vision modules with coupled MRFs
door: Poggio, Tomaso
Gepubliceerd in: (2008)