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