Multi-view alpha matte for free viewpoint rendering

  • Authors:
  • C. Daniel Herrera;Juho Kannala;Janne Heikkilä

  • Affiliations:
  • Machine Vision Group, University of Oulu, Finland;Machine Vision Group, University of Oulu, Finland;Machine Vision Group, University of Oulu, Finland

  • Venue:
  • MIRAGE'11 Proceedings of the 5th international conference on Computer vision/computer graphics collaboration techniques
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a multi-view alpha matting method that requires no user input and is able to deal with any arbitrary scene geometry through the use of depth maps. The algorithm uses multiple observations of the same point to construct constraints on the true foreground color and estimate its transparency. A novel free viewpoint rendering pipeline is also presented that takes advantage of the generated alpha maps to improve the quality of synthesized views over state-of-the-art methods. The results show a clear improvement on image quality by implicitly correcting depth map errors, providing more natural boundaries on transparent regions, and removing artifacts.