• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Context-aware patch-based method for façade inpainting
 
  • Details
  • Full
Options
2020
Konferenzbeitrag
Titel

Context-aware patch-based method for façade inpainting

Abstract
Realistic representations of 3D urban scenes is an important aspect of scene understanding and has many applications. Given untextured polyhedral Level-of-Detail 2 (LoD2) models of building and imaging containing façade textures, occlusions caused by foreground objects are an essential disturbing factor of façade textures. We developed a modification of a well-known patch-based inpainting method and used the knowledge about façade details in order to improve the façade inpainting of occlusions. Our modification focuses on suppression of undesired, superfluous repetitions of textures. To achieve this, a coarse inpainting result by a structural-based method is used to influence the choice of the best patch so that homogeneous regions are preferred. The coarse inpainting is calculated using the context knowledge and average color instead of traditionally applied arbitrary structural inpainting. Our modification furthermore introduces a parameter that allows to weight the influence of the coarse inpainting. A parameter study shows that this parameter can be chosen intuitively and does not require any parameter choice method. The cleaned façade textures could be successfully integrated into the accordingly adjusted building models thus upgrading them to LoD3.
Author(s)
Kottler, Benedikt
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Bulatov, Dimitri
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Xingzi, Zhang
Fraunhofer Singapore
Hauptwerk
15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Proceedings. Vol.1: GRAPP
Konferenz
International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) 2020
International Conference on Computer Graphics Theory and Applications (GRAPP) 2020
DOI
10.5220/0008874802100218
File(s)
N-582946.pdf (5.09 MB)
Language
Englisch
google-scholar
IOSB
Singapore
Tags
  • city modeling

  • inpainting

  • patch-based inpaintin...

  • texture image

  • Lead Topic: Smart Cit...

  • Research Line: Comput...

  • Research Line: Machin...

  • image enhancement

  • context aware computi...

  • image-based reconstru...

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022