Structure-preserving manipulation of photographs

Alexandrina Orzan 1 Adrien Bousseau 1 Pascal Barla 1 Joëlle Thollot 1
1 ARTIS - Acquisition, representation and transformations for image synthesis
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Visual content is often better communicated by simplified or exaggerated images than by the "real world like" images. In this paper, we offer a tool for creating such enhanced representations of photographs in a way consistent with the original image content. To do so, we develop a method to identify the relevant image strucures and their importance. Our approach (a) uses edges as the basic structural unit in the image, (b) proposes tools to manipulate this structure in a flexible way, and (c) employs gradient domain image processing techniques to reconstruct the final image from a "cropped" gradient information. This edge-based approach to non-photorealistic image processing is made feasible by two new techniques we introduce: an addition to the Gaussian scale space theory to compute a perceptually meaningful hierarchy of structures, and a contrast estimation method necessary for faithful gradient-based reconstructions. We finally present various applications that manipulate image structure in different ways.
Keywords : visual communication multiscale analysis image processing image reconstruction
Type de document :
Communication dans un congrès
International Symposium on Non-Photorealistic Animation and Rendering (NPAR), Aug 2007, San Diego, United States. ACM, pp.103-110, 2007, 〈10.1145/1274871.1274888〉
Liste complète des métadonnées

bee_mask.jpg
bee_mask.jpg
bee_teaser.jpg
bee_teaser.jpg
reblur.jpg
reblur.jpg
style.jpg
style.jpg
https://hal.inria.fr/inria-00362868
Contributeur : Pascal Barla <>
Soumis le : vendredi 29 avril 2011 - 10:26:35
Dernière modification le : mercredi 11 avril 2018 - 01:58:03
Document(s) archivé(s) le : samedi 30 juillet 2011 - 02:24:28

Fichiers

photo_manipulation_npar2007.pd...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

INRIA | LJK_GI | LJK_GI_ARTIS | LJK | UGA

Citation

Alexandrina Orzan, Adrien Bousseau, Pascal Barla, Joëlle Thollot. Structure-preserving manipulation of photographs. International Symposium on Non-Photorealistic Animation and Rendering (NPAR), Aug 2007, San Diego, United States. ACM, pp.103-110, 2007, 〈10.1145/1274871.1274888〉. 〈inria-00362868〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

584

Téléchargements de fichiers

1264

Contact


archive-ouverte@inria.fr