miun.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Virtual View Synthesis Using Layered Depth Image Generation and Depth-Based Inpainting for Filling Disocclusions and Translucent Disocclusions
Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems. (Realistic3D)
Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems. (Realistic3D)
Mid Sweden University, Faculty of Science, Technology and Media, Department of Information and Communication systems. (Realistic3D)
2016 (English)In: Journal of Visual Communication and Image Representation, ISSN 1047-3203, E-ISSN 1095-9076, Vol. 38, 351-366 p.Article in journal (Refereed) Published
Abstract [en]

View synthesis is an efficient solution to produce content for 3DTV and FTV. However, proper handling of the disocclusions is a major challenge in the view synthesis. Inpainting methods offer solutions for handling disocclusions, though limitations in foreground-background classification causes the holes to be filled with inconsistent textures. Moreover, the state-of-the art methods fail to identify and fill disocclusions in intermediate distances between foreground and background through which background may be visible in the virtual view (translucent disocclusions). Aiming at improved rendering quality, we introduce a layered depth image (LDI) in the original camera view, in which we identify and fill occluded background so that when the LDI data is rendered to a virtual view, no disocclusions appear but views with consistent data are produced also handling translucent disocclusions. Moreover, the proposed foreground-background classification and inpainting fills the disocclusions with neighboring background texture consistently. Based on the objective and subjective evaluations, the proposed method outperforms the state-of-the art methods at the disocclusions.

Place, publisher, year, edition, pages
2016. Vol. 38, 351-366 p.
Keyword [en]
View synthesis, depth-image based rendering, image inpainting, texture synthesis, hole lling, disocclusions, translucent disocclusions, layered depth image
National Category
Information Systems Media and Communication Technology
Identifiers
URN: urn:nbn:se:miun:diva-27124DOI: 10.1016/j.jvcir.2016.02.017ISI: 000377149100030Scopus ID: 2-s2.0-84977648945Local ID: STCOAI: oai:DiVA.org:miun-27124DiVA: diva2:906337
Available from: 2016-02-24 Created: 2016-02-24 Last updated: 2017-06-30Bibliographically approved

Open Access in DiVA

Accepted version(826 kB)141 downloads
File information
File name FULLTEXT01.pdfFile size 826 kBChecksum SHA-512
821a124edd2c616c5d728229f96826c501a29d2c3ca85dc439058666d1ef0cf3e091f06c21f1cb932be61e40f3f1bc00ecddb5c5b1d75bdf426293226bad025d
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Muddala, Suryanarayana M.Sjöström, MårtenOlsson, Roger
By organisation
Department of Information and Communication systems
In the same journal
Journal of Visual Communication and Image Representation
Information SystemsMedia and Communication Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 141 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 562 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf