Skip to content

Latest

Introducing SLIM: Scalable Lightweight Interactive Models

How to Set Up Spending Limits and Notifications on Roblox

How to Set Up a Parent Account and Link It to Your Child’s

How to Set the Content Maturity Level for Your Child

How to Manage Your Child’s Communication and Chat Settings

How to Use Roblox’s Reporting and Blocking Tools

More results

Real-time Facial Animation for 3D Stylized Character with Emotion Dynamics

View Publication

Author

Ye Pan (Shanghai Jiao Tong University), Ruisi Zhang (Shanghai Jiao Tong University), Jingying Wang (Shanghai Jiao Tong University), Yu Ding (Netease Fuxi AI Lab), Kenny Mitchell (Roblox, Edinburgh Napier University)

Venue

ACM

Abstract

Our aim is to improve animation production techniques' efficiency and effectiveness. We present two real-time solutions which drive character expressions in a geometrically consistent and perceptually valid way. Our first solution combines keyframe animation techniques with machine learning models. We propose a 3D emotion transfer network makes use of a 2D human image to generate a stylized 3D rig parameter. Our second solution combines blendshape-based motion capture animation techniques with machine learning models. We propose a blendshape adaption network which generates the character rig parameter motions with geometric consistency and temporally stability. We demonstrate the effectiveness of our system by comparing it to a commercial product Faceware. Results reveal that ratings of the recognition, intensity, and attractiveness of expressions depicted for animated characters via our systems are statistically higher than Faceware. Our results may be implemented into the animation pipeline, supporting animators to create expressions more rapidly and precisely.