An Adaptive Sampling Method for Layered Depth Image

  • Authors:
  • Ravinder Namboori;Hung Chuan Teh;Zhiyong Huang

  • Affiliations:
  • National University of Singapore;National University of Singapore;National University of Singapore

  • Venue:
  • CGI '04 Proceedings of the Computer Graphics International
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

Sampling issue is an important problem in image basedrendering. In this paper, we propose an adaptivesampling method to improve the Layered Depth Imageframework. Different from the existing methods ofinterpolating or splatting neighboring pixels, our methodselects a set of sampling views based on the sceneanalysis that can guarantee the final rendering quality.Furthermore, the rendering speed is accelerated by thepre-computed patch lookup table, which simplifies thereference view selection process to a simple lookup of ahash table. We have implemented our method. Theexperiment study shows the advantage of the method.