Symmetry-based façade repair

Przemyslaw Musialski, Peter Wonkaz, Meinrad Recheis, Stefan Maierhofer, Werner Purgathofer

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

22 Scopus citations

Abstract

In this paper we address the problem of removing unwanted image content in a single orthographic fa̧ade image. We exploit the regular structure present in building fa̧ades and introduce a diffusion process that is guided by the symmetry prevalent in the image. It removes larger unwanted image objects such as traffic lights, street signs, or cables as well as smaller noise, such as reflections in the windows. The output is intended as source for textures in urban reconstruction projects.

Original languageEnglish (US)
Title of host publicationVMV 2009 - Proceedings of the Vision, Modeling, and Visualization Workshop 2009
Pages3-10
Number of pages8
StatePublished - 2009
Externally publishedYes
Event14th International Conference on Vision, Modeling, and Visualization, VMV 2009 - Braunschweig, Germany
Duration: Nov 16 2009Nov 18 2009

Publication series

NameVMV 2009 - Proceedings of the Vision, Modeling, and Visualization Workshop 2009

Other

Other14th International Conference on Vision, Modeling, and Visualization, VMV 2009
Country/TerritoryGermany
CityBraunschweig
Period11/16/0911/18/09

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Modeling and Simulation

Fingerprint

Dive into the research topics of 'Symmetry-based façade repair'. Together they form a unique fingerprint.

Cite this