Jaroslav Křivánek

Machine Learning and Rendering

SIGGRAPH 2018 Course

Alexander Keller
Jaroslav Křivánek
Charles University, Prague
Render Legion | Chaos Group
Jan Novák
Disney Research
Anton Kaplanyan
Oculus Research
Marco Salvi

(hovering mouse over a presenter's name shows his bio sketch)

teaser1 teaser2

Left: Simple path tracing (left) combined with simple reinforcement learning (middle) outperforms even the much more complicated Metropolis light transport algorithm (right) at the same computational budget. Right: Path guiding based on online learning of parametric mixture models dramatically increases the efficiency of light transport simulation both in simple and complex scenes.


Machine learning techniques just recently enabled dramatic improvements in both realtime and offline rendering. In this course, we introduce the basic principles of machine learning and review their relations to rendering. Besides fundamental facts like the mathematical identity of reinforcement learning and the rendering equation, we cover efficient and surprisingly elegant solutions to light transport simulation, participating media, and noise removal... Extended abstract


Alexander Keller, Jaroslav Křivánek, Jan Novák, Anton Kaplanyan, and Marco Salvi. Machine learning and rendering. ACM SIGGRAPH 2018 Courses (SIGGRAPH '18). ACM, New York, NY, USA.
DOI | BibTeX

Presented on Thursday, 16 August 20182pm - 5:15pm in East Building, Ballroom BC, Vancouver Convention Centre.

Course Notes

1.  From Machine Learning to Graphics and back (Alexander Keller)
pdf slides (pdf)
2.  Path guiding by machine learning (Jaroslav Křivánek)
pptx slides (pptx) | pdf slides (pdf) | pdf notes pages
3.  Deep Learning for Light Transport Simulation (Jan Novák)
pdf notes pages
4.  Real-Time Neural Rendering in Image Space (Anton Kaplanyan)
pdf slides
5.  Current and Future Research Topics (Marco Salvi)


The work was supported by the Charles University grant SVV-2017-260452 and by the Czech Science Foundation grant 16-18964S.