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...
Үндсэн зохиолчид: | Kohli, P, Shekhovtsov, A, Rother, C, Kolmogorov, V, Torr, P |
---|---|
Формат: | Conference item |
Хэл сонгох: | English |
Хэвлэсэн: |
Association for Computing Machinery
2008
|
Ижил төстэй зүйлс
Ижил төстэй зүйлс
-
Reduce, reuse and recycle: efficiently solving multi-label MRFs
-н: Alahari, K, зэрэг
Хэвлэсэн: (2008) -
An analysis of convex relaxations for MAP estimation of discrete MRFs
-н: Pawan Kumar, M, зэрэг
Хэвлэсэн: (2009) -
Dynamic hybrid algorithms for MAP inference in discrete MRFs
-н: Alahari, K, зэрэг
Хэвлэсэн: (2009) -
A tiered move-making algorithm for general pairwise MRFs
-н: Vineet, V, зэрэг
Хэвлэсэн: (2012) -
Integrating vision modules with coupled MRFs
-н: Poggio, Tomaso
Хэвлэсэн: (2008)