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...
主要な著者: | Kohli, P, Shekhovtsov, A, Rother, C, Kolmogorov, V, Torr, P |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
Association for Computing Machinery
2008
|
類似資料
-
Reduce, reuse and recycle: efficiently solving multi-label MRFs
著者:: Alahari, K, 等
出版事項: (2008) -
An analysis of convex relaxations for MAP estimation of discrete MRFs
著者:: Pawan Kumar, M, 等
出版事項: (2009) -
Dynamic hybrid algorithms for MAP inference in discrete MRFs
著者:: Alahari, K, 等
出版事項: (2009) -
A tiered move-making algorithm for general pairwise MRFs
著者:: Vineet, V, 等
出版事項: (2012) -
Integrating vision modules with coupled MRFs
著者:: Poggio, Tomaso
出版事項: (2008)