Year: 2022
Type: conference-paper
Abstract: Our purpose is to improve performance-based animation which can drive believable$3\mathrm{D}$stylized characters that are truly perceptual. By combining traditional blendshape animation techniques with machine learning models, we present a real time motion capture system, called MienCap, which drive character expressions in a geometrically consistent and perceptually valid way. We demon-strate the effectiveness of our system by comparing to a commercial product Faceware. Results reveal that ratings of the recognition of expressions depicted for animated characters via our systems are statistically higher than Faceware. Our results may be implemented into the VR filmmaking and animation pipeline, and provide animators with a system for creating the expressions they wish to use more quickly and accurately.
Authors: Ye Pan, Ruisi Zhang, Jingying Wang, Nengfu Chen, Yilin Qiu, Yu Ding, Kenny Mitchell
Institutions: Shanghai Jiao Tong University, Edinburgh Napier University
Language: English
Topic: Human Motion and Animation
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4224255443