Robust higher order potentials for enforcing label consistency
This paper proposes a novel framework for labelling problems which is able to combine multiple segmentations in a principled manner. Our method is based on higher order conditional random fields and uses potentials defined on sets of pixels (image segments) generated using unsupervised segmentation...
Κύριοι συγγραφείς: | Kohli, P, Ladický, L, Torr, PHS |
---|---|
Μορφή: | Journal article |
Γλώσσα: | English |
Έκδοση: |
Springer
2009
|
Παρόμοια τεκμήρια
-
Robust higher order potentials for enforcing label consistency
ανά: Kohli, P, κ.ά.
Έκδοση: (2008) -
Exact inference in multi-label CRFs with higher order cliques
ανά: Ramalingam, S, κ.ά.
Έκδοση: (2008) -
P3 and beyond: solving energies with higher order cliques
ανά: Kohli, P, κ.ά.
Έκδοση: (2007) -
Associative hierarchical CRFs for object class image segmentation
ανά: Ladický, L, κ.ά.
Έκδοση: (2009) -
Exact and approximate inference in associative hierarchical networks using graph cuts
ανά: Russell, C, κ.ά.
Έκδοση: (2010)