Physically based facial expression synthesizer with performance analysis and GPU-aided simulation
C. Chen, Edmond C. Prakash · 2006
The performance analysis of a physically-based facial expression synthesizer with a novel algorithm for designing parametric muscle model is described. The facial expression synthesizer is partitioned into four general activities: construction of volumetric soft tissue layer, design of underlying volumetric facial musculature, ensemble of muscles to synthesize the facial expression and an efficient and stable numerical integration for dynamic skin deformation. We present techniques for analyzing the performance of facial expression systems in general and in particular the performance for various stages in our system. We also highlight potential improvements in performance that is possible using the powerful GPUs.