A variational framework for exemplar-based image inpainting

Journal Article (Journal Article)

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 nonlocal 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. © 2010 Springer Science+Business Media, LLC.

Full Text

Duke Authors

Cited Authors

  • Arias, P; Facciolo, G; Caselles, V; Sapiro, G

Published Date

  • July 1, 2011

Published In

Volume / Issue

  • 93 / 3

Start / End Page

  • 319 - 347

Electronic International Standard Serial Number (EISSN)

  • 1573-1405

International Standard Serial Number (ISSN)

  • 0920-5691

Digital Object Identifier (DOI)

  • 10.1007/s11263-010-0418-7

Citation Source

  • Scopus