Truncated max-of-convex models
Truncated convex models (TCM) are a special case of pairwise random fields that have been widely used in computer vision. However, by restricting the order of the potentials to be at most two, they fail to capture useful image statistics. We propose a natural generalization of TCM to high-order rand...
Huvudupphovsmän: | Pansari, P, Mudigonda, P |
---|---|
Materialtyp: | Conference item |
Publicerad: |
Computer Vision Foundation
2017
|
Liknande verk
-
Truncated max-of-convex models
av: Mudigonda, P, et al.
Publicerad: (2017) -
Improved moves for truncated convex models
av: Kumar, MP, et al.
Publicerad: (2009) -
Improved moves for truncated convex models
av: Pawan Kumar, M, et al.
Publicerad: (2011) -
Optimal submodular extensions for marginal estimation
av: Pansari, P, et al.
Publicerad: (2018) -
On hyperspaces of max-plus and max-min convex sets
av: Bazylevych Lidiya, et al.
Publicerad: (2017-01-01)