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...
Autors principals: | Pansari, P, Mudigonda, P |
---|---|
Format: | Conference item |
Publicat: |
Computer Vision Foundation
2017
|
Ítems similars
-
Truncated max-of-convex models
per: Mudigonda, P, et al.
Publicat: (2017) -
Improved moves for truncated convex models
per: Kumar, MP, et al.
Publicat: (2009) -
Improved moves for truncated convex models
per: Pawan Kumar, M, et al.
Publicat: (2011) -
Optimal submodular extensions for marginal estimation
per: Pansari, P, et al.
Publicat: (2018) -
On hyperspaces of max-plus and max-min convex sets
per: Bazylevych Lidiya, et al.
Publicat: (2017-01-01)