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...
Main Authors: | Pansari, P, Mudigonda, P |
---|---|
格式: | Conference item |
出版: |
Computer Vision Foundation
2017
|
相似書籍
-
Truncated max-of-convex models
由: Mudigonda, P, et al.
出版: (2017) -
Improved moves for truncated convex models
由: Kumar, MP, et al.
出版: (2009) -
Improved moves for truncated convex models
由: Pawan Kumar, M, et al.
出版: (2011) -
Optimal submodular extensions for marginal estimation
由: Pansari, P, et al.
出版: (2018) -
On hyperspaces of max-plus and max-min convex sets
由: Bazylevych Lidiya, et al.
出版: (2017-01-01)