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 |
---|---|
פורמט: | Conference item |
שפה: | English |
יצא לאור: |
Association for Computing Machinery
2008
|
פריטים דומים
-
Reduce, reuse and recycle: efficiently solving multi-label MRFs
מאת: Alahari, K, et al.
יצא לאור: (2008) -
An analysis of convex relaxations for MAP estimation of discrete MRFs
מאת: Pawan Kumar, M, et al.
יצא לאור: (2009) -
Dynamic hybrid algorithms for MAP inference in discrete MRFs
מאת: Alahari, K, et al.
יצא לאור: (2009) -
A tiered move-making algorithm for general pairwise MRFs
מאת: Vineet, V, et al.
יצא לאור: (2012) -
Integrating vision modules with coupled MRFs
מאת: Poggio, Tomaso
יצא לאור: (2008)