GDC is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

View, browse and sort the ever-growing list of sessions by pass type, topic, and format. All registered attendees will be able to build their personal schedule in the mobile event app, once live early 2022.

GDC Masterclass courses require a paid pass to attend. Class sizes are kept intentionally small and seats are limited to ensure every student receives one-on-one assistance from the instructor. Pass pricing per course varies, please review the passes and pricing page for more details and secure your spot today!

Machine Learning Summit: Emotion Detection for Expressive Characters in 'Marvel's Guardians of the Galaxy'

Romain Trachel  (Senior Machine Learning Specialist, Eidos Sherbrooke)

Pass Type: All Access Pass, Summits Pass - Get your pass now!

Topic: Programming

Format: Session

Vault Recording: TBD

Audience Level: No

Romain Trachel (PhD) is going to present a machine learning project in collaboration with a production team at Eidos Montréal for the game development of Marvel's Guardians of the Galaxy. He will talk about emotions and facial expression recognition, share his experience with model deployment in the build system to bake animation curves of actors emotions. At runtime, the animation system use these curves to control the guardians body/language for enriching traversal gameplay with entertaining dialogues. This project saved hours of annotation work to senior animators during the production and let them focus on more creative work.

Takeaway

Attendees will learn how facial expression recognition models can be deployed in production. Romain will talk about face landmark extraction, hyper-parameter tuning, model interpretation and python tools like scikit-learn for pipeline deployment. It is not an official marvel communication.

Intended Audience

This talk is intended for a public with basic knowledge about machine learning and animation. It will be understandable to professional game developers and producers.