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...
المؤلفون الرئيسيون: | Kohli, P, Ladický, L, Torr, PHS |
---|---|
التنسيق: | Journal article |
اللغة: | English |
منشور في: |
Springer
2009
|
مواد مشابهة
-
Robust higher order potentials for enforcing label consistency
حسب: Kohli, P, وآخرون
منشور في: (2008) -
Exact inference in multi-label CRFs with higher order cliques
حسب: Ramalingam, S, وآخرون
منشور في: (2008) -
P3 and beyond: solving energies with higher order cliques
حسب: Kohli, P, وآخرون
منشور في: (2007) -
Associative hierarchical CRFs for object class image segmentation
حسب: Ladický, L, وآخرون
منشور في: (2009) -
Exact and approximate inference in associative hierarchical networks using graph cuts
حسب: Russell, C, وآخرون
منشور في: (2010)