Stochastic Substitute Trees for Real-Time Global Illumination

Wolfgang Tatzgern, Benedikt Mayr, Bernhard Kerbl, Markus Steinberger
Stochastic Substitute Trees for Real-Time Global Illumination
In Symposium on Interactive 3D Graphics and Games, pages 1-9. May 2020.

Information

Abstract

With the introduction of hardware-supported ray tracing and deep learning for denoising, computer graphics has made a considerable step toward real-time global illumination. In this work, we present an alternative global illumination method: The stochastic substitute tree (SST), a hierarchical structure inspired by lightcuts with light probability distributions as inner nodes. Our approach distributes virtual point lights (VPLs) in every frame and efficiently constructs the SST over those lights by clustering according to Morton codes. Global illumination is approximated by sampling the SST and considers the BRDF at the hit location as well as the SST nodes’ intensities for importance sampling directly from inner nodes of the tree. To remove the introduced Monte Carlo noise, we use a recurrent autoencoder. In combination with temporal filtering, we deliver real-time global illumination for complex scenes with challenging light distributions.

Additional Files and Images

Additional images and videos


Additional files

Weblinks

BibTeX

@inproceedings{tatzgern-2020-sst,
  title =      "Stochastic Substitute Trees for Real-Time Global
               Illumination",
  author =     "Wolfgang Tatzgern and Benedikt Mayr and Bernhard Kerbl and
               Markus Steinberger",
  year =       "2020",
  abstract =   "With the introduction of hardware-supported ray tracing and
               deep learning for denoising, computer graphics has made a
               considerable step toward real-time global illumination. In
               this work, we present an alternative global illumination
               method: The stochastic substitute tree (SST), a hierarchical
               structure inspired by lightcuts with light probability
               distributions as inner nodes. Our approach distributes
               virtual point lights (VPLs) in every frame and efficiently
               constructs the SST over those lights by clustering according
               to Morton codes. Global illumination is approximated by
               sampling the SST and considers the BRDF at the hit location
               as well as the SST nodes’ intensities for importance
               sampling directly from inner nodes of the tree. To remove
               the introduced Monte Carlo noise, we use a recurrent
               autoencoder. In combination with temporal filtering, we
               deliver real-time global illumination for complex scenes
               with challenging light distributions.",
  month =      may,
  booktitle =  "Symposium on Interactive 3D Graphics and Games",
  event =      "I3D ’20",
  pages =      "1--9",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2020/tatzgern-2020-sst/",
}