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...
Main Authors: | Kohli, P, Ladický, L, Torr, PHS |
---|---|
Format: | Conference item |
Language: | English |
Published: |
IEEE
2008
|
Similar Items
-
Robust higher order potentials for enforcing label consistency
by: Kohli, P, et al.
Published: (2009) -
Exact inference in multi-label CRFs with higher order cliques
by: Ramalingam, S, et al.
Published: (2008) -
P3 and beyond: solving energies with higher order cliques
by: Kohli, P, et al.
Published: (2007) -
Efficient relaxations for dense CRFs with sparse higher-order potentials
by: Joy, T, et al.
Published: (2019) -
P3 & beyond: move making algorithms for solving higher order functions
by: Kohli, P, et al.
Published: (2008)