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...
المؤلفون الرئيسيون: | Kohli, P, Shekhovtsov, A, Rother, C, Kolmogorov, V, Torr, P |
---|---|
التنسيق: | Conference item |
اللغة: | English |
منشور في: |
Association for Computing Machinery
2008
|
مواد مشابهة
-
Reduce, reuse and recycle: efficiently solving multi-label MRFs
حسب: Alahari, K, وآخرون
منشور في: (2008) -
An analysis of convex relaxations for MAP estimation of discrete MRFs
حسب: Pawan Kumar, M, وآخرون
منشور في: (2009) -
Dynamic hybrid algorithms for MAP inference in discrete MRFs
حسب: Alahari, K, وآخرون
منشور في: (2009) -
A tiered move-making algorithm for general pairwise MRFs
حسب: Vineet, V, وآخرون
منشور في: (2012) -
Integrating vision modules with coupled MRFs
حسب: Poggio, Tomaso
منشور في: (2008)