Improved image quality in fast inpainting with omnidirectional filling

Ossi Hirvola, Timo Viitanen, Vicky Sintunata, Terumasa Aoki

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

1 Citation (Scopus)

Abstract

Image inpainting is an active research field of image processing. Previous inpainting methods often require a long computational time to give sufficient results, especially due to the extensive search process of exemplar-based methods. This work improves a previous fast inpainting method based on local similarity, which achieves runtimes measured in tens of milliseconds per image, but often results in unacceptable artifacts. We improve the resulting image quality by allowing pixels to be filled at any angle, determining the angle based only on the vicinity of the target region, and cross-fading between source pixels from opposite sides of the target region. The proposed method is shown to eliminate the two drawbacks, while retaining a fast runtime.

Original languageEnglish
Title of host publication2016 International Conference on Image, Vision and Computing, ICIVC 2016
PublisherIEEE
Pages31-35
Number of pages5
ISBN (Electronic)9781509037544
DOIs
Publication statusPublished - 19 Sep 2016
MoE publication typeA4 Article in a conference publication
EventInternational Conference on Image, Vision and Computing - Portsmouth, United Kingdom
Duration: 3 Aug 20165 Aug 2016

Conference

ConferenceInternational Conference on Image, Vision and Computing
Abbreviated titleICIVC
CountryUnited Kingdom
CityPortsmouth
Period03/08/201605/08/2016

Keywords

  • cross-fade
  • fast inpainting
  • image inpainting
  • local similarity
  • symmetrical similarity

Fingerprint Dive into the research topics of 'Improved image quality in fast inpainting with omnidirectional filling'. Together they form a unique fingerprint.

Cite this