My favorite samples

SIGGRAPH 2019 (course)

What samples are best? Will deterministic samples do the job (a), or are blue noise characteristics required to render images without disturbing artifacts (b)? Can we construct such point sets (c) and sequences (d) in an efficient way? It is important to select the appropriate samples for efficient image synthesis (e).

Abstract

Light transport simulation is ruled by the radiance equation, which is an integral equation. Photorealistic image synthesis consists of computing functionals of the solution of the integral equation, which involves integration, too. However, in meaningful settings, none of the integrals can be computed analytically and, in fact, all these integrals need to be approximated using Monte Carlo and quasi-Monte Carlo methods. Generating uniformly distributed points in the unit-hypercube is at the core of all of these methods. The course teaches the algorithms behind and elaborates on the characteristics of different classes of uniformly distributed points to help selecting the points most efficient for a task.

Downloads and links

BibTeX reference

inproceedings{Keller:2019:MyFavoriteSamples,
  author = {Alexander Keller and Iliyan Georgiev and Abdalla Ahmed and Per Christensen and Matt Pharr},
  title = {My Favorite Samples},
  booktitle = {ACM SIGGRAPH 2019 Courses},
  series = {SIGGRAPH '19},
  year = {2019},
  location = {Los Angeles, California, USA},
  publisher = {ACM},
  address = {New York, NY, USA}
}