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...
Главные авторы: | Kohli, P, Shekhovtsov, A, Rother, C, Kolmogorov, V, Torr, P |
---|---|
Формат: | Conference item |
Язык: | English |
Опубликовано: |
Association for Computing Machinery
2008
|
Схожие документы
-
Reduce, reuse and recycle: efficiently solving multi-label MRFs
по: Alahari, K, и др.
Опубликовано: (2008) -
An analysis of convex relaxations for MAP estimation of discrete MRFs
по: Pawan Kumar, M, и др.
Опубликовано: (2009) -
Dynamic hybrid algorithms for MAP inference in discrete MRFs
по: Alahari, K, и др.
Опубликовано: (2009) -
A tiered move-making algorithm for general pairwise MRFs
по: Vineet, V, и др.
Опубликовано: (2012) -
Integrating vision modules with coupled MRFs
по: Poggio, Tomaso
Опубликовано: (2008)