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.

Use the GDC 2021 Session Viewer to browse and sort the ever-growing list of sessions by day, time, pass type, topic, and format. All registered attendees will be able to build their personal schedule directly within the event platform, once live early July 2021. All times are listed in Pacific Time.

Machine Learning Summit: 3D Parametric Face Model and Its Applications in Games

Pei Li  (Senior AI Researcher, Netease Games AILAB)

Date: Tuesday, July 20

Time: 3:20pm - 3:50pm

Pass Type: All Access Pass, Summits Pass

Topic: Programming

Format: Session

Vault Recording: Video

Audience Level: N/A: I prefer to present live on-site but I am open to delivering a virtual presentation

There always exist a huge demand for high-quality 3D facial assets in the game industry, but producing 3D facial assets is a costly and time-consuming task. Fortunately, some recent research progress on 3D Morphable Face Models (3DMM) can be utilized to facilitate this process (i.e., modeling, rigging and animation). In NetEase Games, we built a custom 3D parametric face model, around which, we developed a series of techniques for 3D facial content-creation and in-game applications. This session will introduce what is and how to build such a 3D parametric face model, and give implementation details to three techniques built upon this model, i.e., creating face meshes from images, producing shape and expression variations from one example face mesh, and facial performance capture.


Attendees will learn what is a 3D parametric face model, how to build a 3D parametric face model, and how to utilize this model for 3D facial content-creation and in-game applications.

Intended Audience

This presentation is intended for researchers and developers working on "faces", who want to learn how a parametric face model can be practically used in games, and artists who want to learn how their production efficiency can be potentially improved by this technique.