Scalable multi-class sampling via filtered sliced optimal transport

SIGGRAPH Asia 2022 (journal)

Demonstration of our multi-class sampling framework on three applications. Left: CMYK color stippling involves optimizing for 15 classes, each following a different, non-uniform density. Middle: 7 colors of trees and their union optimized jointly. Right: Distributing rendering error as blue noise, cast as a multi-class problem (4096 classes), showing improved visual fidelity over traditional uncorrelated-pixel sampling.

Abstract

We propose a multi-class point optimization formulation based on continuous Wasserstein barycenters. Our formulation is designed to handle hundreds to thousands of optimization objectives and comes with a practical optimization scheme. We demonstrate the effectiveness of our framework on various sampling applications like stippling, object placement, and Monte-Carlo integration. We a derive multi-class error bound for perceptual rendering error which can be minimized using our optimization.

Downloads and links

Media

Fast-forward video

Summary video

Talk video

BibTeX reference

@article{Salaun:2022:ScalableMultiClassSampling,
  author = {Corentin Sala\"un and Iliyan Georgiev and Hans-Peter Seidel and Gurprit Singh},
  title = {Scalable multi-class sampling via filtered sliced optimal transport},
  journal = {ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia)},
  year = {2022},
  volume = {41},
  number = {6},
  doi = {10.1145/3550454.3555484}
}