Nontexture inpainting by curvature-driven diffusions

Tony F. Chan*, Jianhong Shen

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

879 Scopus citations

Abstract

Inpainting is an image interpolation problem, often referring to interpolations over large-scale missing domains. In this paper, guided by the connectivity principle of human visual perception, we introduce a nonlinear PDE inpainting model based upon curvature-driven diffusions for nontexture images. This third-order PDE model improves the second-order total variation inpainting model introduced earlier by Chan and Shen (SIAM J. Appl. Math., in press, 2001). Computational schemes and digital examples are given.

Original languageEnglish (US)
Pages (from-to)436-449
Number of pages14
JournalJournal of Visual Communication and Image Representation
Volume12
Issue number4
DOIs
StatePublished - Dec 2001
Externally publishedYes

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Nontexture inpainting by curvature-driven diffusions'. Together they form a unique fingerprint.

Cite this