High efficiency depth image-based rendering with simplified inpainting-based hole filling

Pin Chen Kuo, Jhih Ming Lin, Bin Da Liu, Jar Ferr Yang

Research output: Contribution to journalArticlepeer-review

7 Citations (Scopus)

Abstract

Hole and crack filling is the most important issue in depth-image-based rendering (DIBR) algorithms for generating virtual view images when only one view image and one depth map are available. This paper proposes a priority patch inpainting algorithm for hole filling inDIBR algorithms by generatingmultiple virtual views.Atexture-based interpolation method is applied for crack filling. Then, an inpainting-based algorithm is applied patch by patch for hole filling. A prioritized method for selecting the critical patch is also proposed to reduce computation time. Finally, the proposed method is realized on the compute unified device architecture parallel computing platform which runs on a graphics processing unit. Simulation results showthat the proposed algorithm is 51-fold faster for virtual viewsynthesis and achieves better virtual view quality compared to the traditional DIBR algorithm which contains depth preprocessing, warping, and hole filling.

Original languageEnglish
Pages (from-to)623-645
Number of pages23
JournalMultidimensional Systems and Signal Processing
Volume27
Issue number3
DOIs
Publication statusPublished - 2016 Dec 30

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint Dive into the research topics of 'High efficiency depth image-based rendering with simplified inpainting-based hole filling'. Together they form a unique fingerprint.

Cite this