Depth-Based View Synthesis Using Pixel-level Image Inpainting

Shao-Ping Lu, Jan Hanca, Adrian Munteanu, Peter Schelkens

Research output: Chapter in Book/Report/Conference proceedingConference paper

12 Citations (Scopus)

Abstract

Depth-based view synthesis can produce novel realistic images of a scene by view warping and image inpainting. This paper presents a depth-based view synthesis approach performing pixel-level image inpainting. The proposed approach provides great flexibility in pixel manipulation and prevents random effects in texture propagation. By analyzing the process generating image holes in view warping, we firstly classify such areas into simple holes and disocclusion areas. Based on depth information constraints and different strategies for random propagation, an approximate nearest-neighbor match based pixel-level inpainting is introduced to complete holes from the two classes. Experimental results demonstrate that the proposed view synthesis method can effectively produce smooth textures and reasonable structure propagation. The proposed depth-based pixel-level inpainting is well suitable to multi-view video and other higher dimensional view synthesis settings.
Original languageEnglish
Title of host publication2013 18th International Conference on Digital Signal Processing
PublisherIEEE
Pages240-245
Number of pages6
ISBN (Electronic)978-1-4673-5805-7
ISBN (Print)978-1-4673-5806-4
Publication statusPublished - 1 Jul 2013
Event18th International Conference on Digital Signal Processing (DSP 2013) - Santorini, Greece
Duration: 1 Jul 20133 Jul 2013
http://dsp2013.dspconferences.org/

Publication series

NameProceedings of the International Conference on Digital Signal Processing
PublisherIEEE
ISSN (Print)1546-1874

Conference

Conference18th International Conference on Digital Signal Processing (DSP 2013)
CountryGreece
CitySantorini
Period1/07/133/07/13
Internet address

Keywords

  • depth image based rendering
  • view synthesis
  • approximate nearest-neighbor match
  • pixel-level inpainting

Fingerprint

Dive into the research topics of 'Depth-Based View Synthesis Using Pixel-level Image Inpainting'. Together they form a unique fingerprint.

Cite this