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