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...
Главные авторы: | Pansari, P, Mudigonda, P |
---|---|
Формат: | Conference item |
Опубликовано: |
Computer Vision Foundation
2017
|
Схожие документы
Схожие документы
-
Truncated max-of-convex models
по: Mudigonda, P, и др.
Опубликовано: (2017) -
Improved moves for truncated convex models
по: Kumar, MP, и др.
Опубликовано: (2009) -
Improved moves for truncated convex models
по: Pawan Kumar, M, и др.
Опубликовано: (2011) -
Optimal submodular extensions for marginal estimation
по: Pansari, P, и др.
Опубликовано: (2018) -
On hyperspaces of max-plus and max-min convex sets
по: Bazylevych Lidiya, и др.
Опубликовано: (2017-01-01)