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...
Κύριοι συγγραφείς: | Kohli, P, Shekhovtsov, A, Rother, C, Kolmogorov, V, Torr, P |
---|---|
Μορφή: | Conference item |
Γλώσσα: | English |
Έκδοση: |
Association for Computing Machinery
2008
|
Παρόμοια τεκμήρια
-
Reduce, reuse and recycle: efficiently solving multi-label MRFs
ανά: Alahari, K, κ.ά.
Έκδοση: (2008) -
An analysis of convex relaxations for MAP estimation of discrete MRFs
ανά: Pawan Kumar, M, κ.ά.
Έκδοση: (2009) -
Dynamic hybrid algorithms for MAP inference in discrete MRFs
ανά: Alahari, K, κ.ά.
Έκδοση: (2009) -
A tiered move-making algorithm for general pairwise MRFs
ανά: Vineet, V, κ.ά.
Έκδοση: (2012) -
Integrating vision modules with coupled MRFs
ανά: Poggio, Tomaso
Έκδοση: (2008)