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...
Autori principali: | Pansari, P, Mudigonda, P |
---|---|
Natura: | Conference item |
Pubblicazione: |
Computer Vision Foundation
2017
|
Documenti analoghi
Documenti analoghi
-
Truncated max-of-convex models
di: Mudigonda, P, et al.
Pubblicazione: (2017) -
Improved moves for truncated convex models
di: Kumar, MP, et al.
Pubblicazione: (2009) -
Improved moves for truncated convex models
di: Pawan Kumar, M, et al.
Pubblicazione: (2011) -
Optimal submodular extensions for marginal estimation
di: Pansari, P, et al.
Pubblicazione: (2018) -
On hyperspaces of max-plus and max-min convex sets
di: Bazylevych Lidiya, et al.
Pubblicazione: (2017-01-01)