Accéder directement au contenu Accéder directement à la navigation
Chapitre d'ouvrage

Exemplar-Based Image Inpainting using an Affine Invariant Similarity Measure

Abstract : Patch-based approaches are used in state-of-the-art methods for image inpainting. This paper presents a new method for exemplar-based image inpainting using transformed patches. The transformation is determined for each patch in a fully automatic way from a surrounding texture content. We build upon a recent affine invariant patch similarity measure that performs an appropriate patch comparison by automatically adapting the size and shape of the patches. As a consequence, it intrinsically extends the set of available source patches to copy information from. We incorporate this measure into a variational formulation for inpainting and present a numerical algorithm for optimizing it. We show that our method can be applied to complete a perspectively distorted texture as well as to automatically inpaint one view of a scene using other view of the same scene as a source. We present experimental results both for gray and color images, and a comparison with some exemplar-based image inpainting methods.
Liste complète des métadonnées

Littérature citée [38 références]  Voir  Masquer  Télécharger

https://hal-enpc.archives-ouvertes.fr/hal-01829625
Contributeur : Gabriele Facciolo <>
Soumis le : mercredi 4 juillet 2018 - 11:10:18
Dernière modification le : jeudi 2 juillet 2020 - 17:17:18
Archivage à long terme le : : lundi 1 octobre 2018 - 11:06:13

Fichier

CCIS Lecture Notes.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01829625, version 1

Citation

Vadim Fedorov, Pablo Arias, Gabriele Facciolo, Coloma Ballester. Exemplar-Based Image Inpainting using an Affine Invariant Similarity Measure. Computer Vision, Imaging and Computer Graphics Theory and Applications 11th International Joint Conference, VISIGRAPP 2016, Rome, Italy, February 27 – 29, 2016, Revised Selected Papers , 2017, Communications in Computer and Information Science book series. ⟨hal-01829625⟩

Partager

Métriques

Consultations de la notice

284

Téléchargements de fichiers

175