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