International Journal of Computer Vision

, Volume 93, Issue 3, pp 319–347

A Variational Framework for Exemplar-Based Image Inpainting

  • Pablo Arias
  • Gabriele Facciolo
  • Vicent Caselles
  • Guillermo Sapiro
Article

DOI: 10.1007/s11263-010-0418-7

Cite this article as:
Arias, P., Facciolo, G., Caselles, V. et al. Int J Comput Vis (2011) 93: 319. doi:10.1007/s11263-010-0418-7

Abstract

Non-local methods for image denoising and inpainting have gained considerable attention in recent years. This is in part due to their superior performance in textured images, a known weakness of purely local methods. Local methods on the other hand have demonstrated to be very appropriate for the recovering of geometric structures such as image edges. The synthesis of both types of methods is a trend in current research. Variational analysis in particular is an appropriate tool for a unified treatment of local and non-local methods. In this work we propose a general variational framework for non-local image inpainting, from which important and representative previous inpainting schemes can be derived, in addition to leading to novel ones. We explicitly study some of these, relating them to previous work and showing results on synthetic and real images.

Keywords

InpaintingVariational methodsSelf-similarityNon-local methodsExemplar-based methods

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Pablo Arias
    • 1
  • Gabriele Facciolo
    • 1
  • Vicent Caselles
    • 1
  • Guillermo Sapiro
    • 2
  1. 1.Dept. of Information and Communication TechnologiesUniversitat Pompeu FabraBarcelonaSpain
  2. 2.Dept. of Electrical and Computer EngineeringUniversity of MinnesotaMinneapolisUSA