Jaroslav Křivánek

Path guiding in production

SIGGRAPH 2019 Course

Jiří Vorba Weta Digital

Johannes Hanika Karlsruhe Institute of Technology

Sebastian Herholz University of Tübingen

Thomas Müller NVIDIA

Jaroslav Křivánek Charles University, Prague Chaos Czech a. s.

Alexander Keller NVIDIA

Path guiding allows efficient rendering of notoriously difficult light transport conditions. These production shots from Alita: Battle Angel show its versatility. We were able to apply it on close-up shots of Alita’s eyes featuring specular-diffuse-specular caustics as well as on vast underwater scenes with god-rays and caustics on the lake bed, in the volume, and on the main character. ©2018 Twentieth Century Fox Film Corporation. All rights reserved.

Abstract

Path guiding is a family of adaptive variance reduction techniques in physically-based rendering, which includes methods for sampling both direct and indirect illumination, surfaces and volumes but also for sampling optimal path lengths and making splitting decisions. Since adoption of path tracing as a de facto standard in the VFX industry several years ago, there has been an increased interest in producing high-quality images with low amount of Monte Carlo samples per pixel. Path guiding, which has received attention in the research community in the past few years, has proven to be useful for this task and therefore has been adopted by Weta Digital. Recently, it has also been implemented in the Walt Disney Animation Studios' Hyperion and Pixar's Renderman. The goal of this course is to share our practical experience with path guiding in production and to provide self-contained overview of recently published techniques and to discuss their pros and cons. We also take audience through theoretical background of various path guiding methods which are mostly based on machine learning - used to adapt sampling distributons based on observed samples - and zero-variance random walk theory - used as a framework for combining different sampling decisions in an optimal way. At the end of our course we discuss open problems and invite researchers to further develop path guiding in their future work. ... Extended abstract

Reference

Jiří Vorba, Johannes Hanika, Sebastian Herholz, Thomas Müller, Jaroslav Křivánek, and Alexander Keller. Path Guiding in Production. ACM SIGGRAPH 2019 Courses (SIGGRAPH '19). ACM, New York, NY, USA.
DOI | BibTeX

Presented on Sunday, 28 July 2019, 2pm - 5:15pm in Room 403AB, Los Angeles Convention Centre.

Course Materials

1.  Introduction and Overview (Jiří Vorba) 2.  Guiding Indirect Illumination - An Overview (Jiří Vorba) slides (pdf) 3.  Bayesian Learning for Guided Direct Illumination (Jaroslav Křivánek) slides (pptx) | slides (pdf) | notes pages 4.  Guiding and Shadow Rays (Alexander Keller) slides (pdf) 5.  "Practical Path Guiding" in Production (Thomas Müller) slides (keynote) | notes pages 6.  Volumetric Path Guiding (Based on Zero-Variance Random Walk Theory) (Sebastian Herholz) slides (pdf) 7.  Selective guided sampling with complete light transport paths (Johannes Hanika) slides (pdf)

extended abstract pdf (1 MB)   written course notes pdf (28 MB)

Acknowledgements