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