Prior and macro-filling order for image completion

Raul Martinez-Noriega 1 Aline Roumy 1
1 Sirocco - Analysis representation, compression and communication of visual data
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : This paper introduces an algorithm to build priors that help image completion to produce better and visually plausible results. The goal of the prior is to seamlessly reconstruct long edges, that exemplar- based inpainting fails to restore. The prior consists in locating the edges across the missing region, and separating the image in regions of relative similar textures. Unlike other techniques, our proposal does not use segmentation or inpainting to obtain the prior, provid- ing a fast technique. Moreover, the technique does not rely on image dependent threshold. Finally, we propose a scheduling for the syn- thesis of the missing region based on the prior, and Criminisi's algo- rithm. The scheduling may be thought as a novel macro-filling order for exemplar-based synthesis. The results are comparable with re- cent and more complex proposals based on super-resolution or Pho- toshop. Finally, we emphasize that, our prior is not dedicated to our image completion algorithm, and can be used to drive other image completion or inpainting algorithm
Type de document :
Communication dans un congrès
IEEE Intl. Conf. on Image Processing (ICIP), Sep 2013, Melbourne, Australia. 2013
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00918346
Contributeur : Christine Guillemot <>
Soumis le : lundi 12 janvier 2015 - 11:30:31
Dernière modification le : mercredi 11 avril 2018 - 02:00:18
Document(s) archivé(s) le : lundi 13 avril 2015 - 10:06:09

Fichier

13icip_MartinezNoriega_EdgePri...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00918346, version 1

Citation

Raul Martinez-Noriega, Aline Roumy. Prior and macro-filling order for image completion. IEEE Intl. Conf. on Image Processing (ICIP), Sep 2013, Melbourne, Australia. 2013. 〈hal-00918346〉

Partager

Métriques

Consultations de la notice

242

Téléchargements de fichiers

172