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...
मुख्य लेखकों: | Kohli, P, Ladický, L, Torr, PHS |
---|---|
स्वरूप: | Journal article |
भाषा: | English |
प्रकाशित: |
Springer
2009
|
समान संसाधन
-
Robust higher order potentials for enforcing label consistency
द्वारा: Kohli, P, और अन्य
प्रकाशित: (2008) -
Exact inference in multi-label CRFs with higher order cliques
द्वारा: Ramalingam, S, और अन्य
प्रकाशित: (2008) -
P3 and beyond: solving energies with higher order cliques
द्वारा: Kohli, P, और अन्य
प्रकाशित: (2007) -
Associative hierarchical CRFs for object class image segmentation
द्वारा: Ladický, L, और अन्य
प्रकाशित: (2009) -
Exact and approximate inference in associative hierarchical networks using graph cuts
द्वारा: Russell, C, और अन्य
प्रकाशित: (2010)