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...
Egile Nagusiak: | Kohli, P, Ladický, L, Torr, PHS |
---|---|
Formatua: | Journal article |
Hizkuntza: | English |
Argitaratua: |
Springer
2009
|
Antzeko izenburuak
-
Robust higher order potentials for enforcing label consistency
nork: Kohli, P, et al.
Argitaratua: (2008) -
Exact inference in multi-label CRFs with higher order cliques
nork: Ramalingam, S, et al.
Argitaratua: (2008) -
P3 and beyond: solving energies with higher order cliques
nork: Kohli, P, et al.
Argitaratua: (2007) -
Associative hierarchical CRFs for object class image segmentation
nork: Ladický, L, et al.
Argitaratua: (2009) -
Exact and approximate inference in associative hierarchical networks using graph cuts
nork: Russell, C, et al.
Argitaratua: (2010)