Reconstructing an image from its local descriptors

Philippe Weinzaepfel 1 Hervé Jégou 1 Patrick Perez 2
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This paper shows that an image can be approximately reconstructed based on the output of a blackbox local description software such as those classically used for image indexing. Our approach consists first in using an off-the-shelf image database to find patches which are visually similar to each region of interest of the unknown input image, according to associated local descriptors. These patches are then warped into input image domain according to interest region geometry and seamlessly stitched together. Final completion of still missing texture-free regions is obtained by smooth interpolation. As demonstrated in our experiments, visually meaningful reconstructions are obtained just based on image local descriptors like SIFT, provided the geometry of regions of interest is known. The reconstruction allows most often the clear interpretation of the semantic image content. As a result, this work raises critical issues of privacy and rights when local descriptors of photos or videos are given away for indexing and search purpose.
Type de document :
Communication dans un congrès
Computer Vision and Pattern Recognition, Jun 2011, Colorado Springs, United States. 2011
Liste complète des métadonnées

Littérature citée [21 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/inria-00566718
Contributeur : Hervé Jégou <>
Soumis le : vendredi 18 février 2011 - 16:40:00
Dernière modification le : jeudi 11 janvier 2018 - 06:20:10
Document(s) archivé(s) le : samedi 3 décembre 2016 - 15:02:22

Fichiers

weinzaepfel_cvpr11.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00566718, version 2

Collections

Citation

Philippe Weinzaepfel, Hervé Jégou, Patrick Perez. Reconstructing an image from its local descriptors. Computer Vision and Pattern Recognition, Jun 2011, Colorado Springs, United States. 2011. 〈inria-00566718v2〉

Partager

Métriques

Consultations de la notice

1357

Téléchargements de fichiers

5847