Taming a Beast: Using ONNX Runtime in AAA Games
To accelerate machine learning research and to unlock the potential for cutting-edge in-game models, Ubisoft started using Microsoft’s open-source inference library ONNX Runtime in their proprietary engines. This session offers insights into using this solution in game dev scenarios: performance topics, build requirements and processes, threads and memory management, library licenses, open-source contributions and the overall organization around this initiative.
Jean-Simon Lapointe
Jean-Simon Lapointe is a Technical Lead in the Technology Group at Ubisoft Montreal since 2020. As a member of the content creation technologies transversal team, he worked on software that helps production teams integrate machine learning technologies inside their games. Additionally, throughout his 20+ years career, he also worked on computer vision and image processing in various industries.