Presentation

Practical Machine Learning for Rendering: From Research to Deployment
Level Intermediate
Event Type
Course
Keywords
Artificial Intelligence/Machine Learning
Rendering
Recordings
This session WILL NOT be recorded.
Interest Areas
Production & Animation
Research & Education
Registration Levels
Ultimate Supporter
Ultimate Attendee
Exhibitor Ultimate
TimeFriday, 13 August 20219:30am - 10am PDT
Location
DescriptionApplying machine learning to improve graphics rendering or asset pipelines is challenging. Practicalities such as proprietary datasets, network retraining, and deployment issues make it difficult to translate published research into deployed solutions. In this course, industry practitioners at the forefront of this interdisciplinary field discuss and outline potential solutions.
Prerequisites Knowledge of computer graphics pipelines familiarity with game engines/production renderers, beginner's knowledge of machine learning.
Intended Audience Attendees are expected to have a working knowledge of production software and deployment and some knowledge of ML. The takeaways are an overview of tools and resources available to rapidly iterate in this space, along with learnings and pitfalls from industry contributors who are experimenting with ML for graphics applications.