Exact inference in multi-label CRFs with higher order cliques

Abstract : This paper addresses the problem of exactly inferring the maximum a posteriori solutions of discrete multi-label MRFs or CRFs with higher order cliques. We present a framework to transform special classes of multi-label higher order functions to submodular second order boolean functions (referred to as ${\cal F}_s^2$), which can be minimized exactly using graph cuts and we characterize those classes. The basic idea is to use two or more boolean variables to encode the states of a single multi-label variable. There are many ways in which this can be done and much interesting research lies in finding ways which are optimal or minimal in some sense. We study the space of possible encodings and find the ones that can transform the most general class of functions to ${\cal F}_s^2$. Our main contributions are twofold. First, we extend the subclass of submodular energy functions that can be minimized exactly using graph cuts. Second , we show how higher order potentials can be used to improve single view 3D reconstruction results. We believe that our work on exact minimization of higher order energy functions will lead to similar improvements in solutions of other labelling problems.
Type de document :
Communication dans un congrès
CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2008, Anchorage, United States. IEEE, 2008, 〈10.1109/CVPR.2008.4587401〉
Liste complète des métadonnées

Littérature citée [27 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01217304
Contributeur : Karteek Alahari <>
Soumis le : lundi 19 octobre 2015 - 12:24:20
Dernière modification le : lundi 28 mai 2018 - 15:10:06
Document(s) archivé(s) le : jeudi 27 avril 2017 - 06:58:58

Fichier

ramalingam08.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Srikumar Ramalingam, Pushmeet Kohli, Karteek Alahari, Philip H. S. Torr. Exact inference in multi-label CRFs with higher order cliques. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2008, Anchorage, United States. IEEE, 2008, 〈10.1109/CVPR.2008.4587401〉. 〈hal-01217304〉

Partager

Métriques

Consultations de la notice

20

Téléchargements de fichiers

136