| Session Name: | Machine Learning Summit: 3D Parametric Face Model and Its Applications in Games |
| Speaker(s): | Pei Li |
| Company Name(s): | Netease Games AILAB |
| Track / Format: | Machine Learning Summit |
Did you know free users get access to 30% of content from the last 2 years?
Get your team full access to the most up to date GDC content
| Overview: | 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. |
Recommended
