Simultaneous total variation image inpainting and blind deconvolution

Tony Chan*, Andy M. Yip, Frederick E. Park

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

51 Scopus citations

Abstract

We propose a total variation based model for simultaneous image inpainting and blind deconvolution. We demonstrate that the tasks are inherently coupled together and that solving them individually will lead to poor results. The main advantages of our model are that (i) boundary conditions for deconvolution required near the interface between observed and occluded regions are naturally generated through inpainting; (ii) inpainting results are enhanced through deconvolution (as opposed to inpainting blurry images). As a result, ringing effects due to imposing improper boundary conditions and errors due to imperfection of inpainting blurry images are reduced. Moreover, our model can also be used to generate boundary conditions for regular deconvolution problems that yields better results than previous methods.

Original languageEnglish (US)
Pages (from-to)92-102
Number of pages11
JournalInternational Journal of Imaging Systems and Technology
Volume15
Issue number1
DOIs
StatePublished - Oct 5 2005

Keywords

  • Blind deconvolution
  • Deblur
  • Image inpainting
  • Simultaneous model
  • Total variation

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Software
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Simultaneous total variation image inpainting and blind deconvolution'. Together they form a unique fingerprint.

Cite this