Statistically optimized sampling for distributed ray tracing

  • Authors:
  • Mark E. Lee;Richard A. Redner;Samuel P. Uselton

  • Affiliations:
  • Amoco Production Company, Tulsa Research Center, University of Tulsa, Tulsa, Oklahoma;Department of Mathematics, University of Tulsa, Tulsa, Oklahoma;Department of Computer Science, University of Tulsa, Tulsa, Oklahoma

  • Venue:
  • SIGGRAPH '85 Proceedings of the 12th annual conference on Computer graphics and interactive techniques
  • Year:
  • 1985

Quantified Score

Hi-index 0.00

Visualization

Abstract

Cook, Porter, and Carpenter coined the phrase "distributed ray tracing" to describe a technique for using each ray of a super-sampled ray tracing procedure as a sample in several dimensions to achieve effects such as penumbras and motion blur in addition to spatial anti-aliasing. The shade to be displayed at a pixel is a weighted integral of the image function. The purpose of using many rays per pixel is to estimate the value of this integral. In this work, a relationship between the number of sample rays and the quality of the estimate of this integral is derived. Furthermore, the number of rays required does not depend on the dimensionality of the space being sampled, but only on the variance of the multi-dimensional image function. The algorithm has been optimized through the use of statistical testing and stratified sampling.