Variational Framework for Non-Local Inpainting

• article
• demo
• archive

BibTeX info

Communicated by Jacques Froment
Demo edited by Gabriele Facciolo

Abstract

Image inpainting aims to obtain a visually plausible image interpolation in a region of the image in which data is missing due to damage or occlusion. Usually, the only available information is the portion of the image outside the inpainting domain. Besides its numerous applications,the inpainting problem is of theoretical interest since its analysis involves an understanding of the self-similarity present in natural images. In this work, we present a detailed description and implementation of three exemplar-based inpainting methods derived from the variational framework introduced by Arias et al.

Download

• full text manuscript: PDF low-res. (733.1K) PDF (1.6M) ^[?]
• source code: TGZ SWHID info
  Software Heritage Archive @softwareversion{sw-ipol.2015.136, title = {{Variational Framework for Non-Local Inpainting}}, author = {Vadim Fedorov, Gabriele Facciolo, Pablo Arias}, date = {2015-04-13}, license = {BSD-2-Clause}, version = {1.1}, swhid = {swh:1:dir:2420ed0c2ccd8f01056a2f1f2308116eeb04acd3;origin=https://doi.org/10.5201/ipol.2015.136;visit=swh:1:snp:cd17b44a9362f96e75f6dea3e60016c26e518f29;anchor=swh:1:rel:74096c4d35ee95479d5c12eeaf934ea8318ad7b0}, related = {ipol.2015.136}, relatedtype = "Reference article: https://doi.org/10.5201/ipol.2015.136" } % the biblatex-software style extension is recommended for software bibitems
  Copy to clipboard

History

• Note from the editor: The source code was updated on March 15, 2016 to fix a bug causing a problem when reading 4-channel images. The original source code can be found here.