A Comprehensive Framework for Image Inpainting

被引：185

作者：

Bugeau, Aurelie ^{[1
]}

Bertalmio, Marcelo ^{[2
]}

Caselles, Vicent ^{[2
]}

Sapiro, Guillermo ^{[3
]}

机构：

[1] Barcelona Media Ctr Innovacio, Barcelona 08018, Spain

[2] Univ Pompeu Fabra, Dept Tecnol Informacio & Comunicac, Barcelona 08002, Spain

[3] Univ Minnesota, Dept Elect & Comp Engn, Minneapolis, MN 55455 USA

来源：

IEEE TRANSACTIONS ON IMAGE PROCESSING | 2010年 / 19卷 / 10期

基金：

美国国家科学基金会;

关键词：

Image inpainting; partial differential equations (PDEs); texture synthesis; variational models; REGULARIZATION;

D O I：

10.1109/TIP.2010.2049240

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Inpainting is the art of modifying an image in a form that is not detectable by an ordinary observer. There are numerous and very different approaches to tackle the inpainting problem, though as explained in this paper, the most successful algorithms are based upon one or two of the following three basic techniques: copy-and-paste texture synthesis, geometric partial differential equations (PDEs), and coherence among neighboring pixels. We combine these three building blocks in a variational model, and provide a working algorithm for image inpainting trying to approximate the minimum of the proposed energy functional. Our experiments show that the combination of all three terms of the proposed energy works better than taking each term separately, and the results obtained are within the state-of-the-art.

引用

页码：2634 / 2645

页数：12