Automatic blend shape creation for facial motion capture

Abstract

Blend shape animation is one of the most common methods for facial animation used by animators. Creation of effective blend shapes is an investment as they can take a very long time to create, but once finished, help with consistency in animation. As this is a prime animation method, its extensive process can be off-putting to newcomers. This project is focused on creating a system that will automate the blend shape creation process. The resulting blend shapes could be used in a blend shape based facial motion capture system (eg. [Weise et al. 2011]). The goal of this application is to produce a comparable result to that of blend shapes done by hand for student projects.