Unsupervised co-segmentation through region matching

Abstract : Co-segmentation is defined as jointly partitioning multiple images depicting the same or similar object, into foreground and background. Our method consists of a multiple-scale multiple-image generative model, which jointly estimates the foreground and background appearance distributions from several images, in a non-supervised manner. In contrast to other co-segmentation methods, our approach does not require the images to have similar foregrounds and different backgrounds to function properly. Region matching is applied to exploit inter-image information by establishing correspondences between the common objects that appear in the scene. Moreover, computing many-to-many associations of regions allow further applications, like recognition of object parts across images. We report results on iCoseg, a challenging dataset that presents extreme variability in camera viewpoint, illumination and object deformations and poses. We also show that our method is robust against large intra-class variability in the MSRC database.
Type de document :
Communication dans un congrès
25th IEEE Conference on Computer Vision and Pattern Recognition - CVPR 2012, Jun 2012, Rhode Island, United States. pp.749-756, 2012
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00856291
Contributeur : Enzo Ferrante <>
Soumis le : vendredi 30 août 2013 - 17:21:27
Dernière modification le : mardi 5 février 2019 - 13:52:14

Identifiants

  • HAL Id : hal-00856291, version 1

Collections

Citation

Jose Rubio, Joan Serrat, Antonio López, Nikos Paragios. Unsupervised co-segmentation through region matching. 25th IEEE Conference on Computer Vision and Pattern Recognition - CVPR 2012, Jun 2012, Rhode Island, United States. pp.749-756, 2012. 〈hal-00856291〉

Partager

Métriques

Consultations de la notice

219