Abstract
The original approach of direct manipulation blendshapes introduced a mathematical framework for manipulating blendshape face models directly and interactively while interoperating with traditional slider-based editing. This article introduces a few practical and useful techniques to the original work and presents the implementation details as a software tool. In addition, this article describes a statistical-prior algorithm that “learns” from previous animation and allows rapid creation of expressive animation in a given style. The animation examples illustrate how effectively this tool works for practical use.
Acknowledgments
The authors would like to thank Atsushi Sato and Makoto Sato for creating the animation examples. We also thank Ayumi Kimura and Jaewoo Seo for discussions and help. This work was partially supported by the Japan Science and Technology Agency's Core Research of Evolutional Science and Technology project.
Notes
1All the supplemental videos are found at the address listed at the end of this paper.
2Also, you can see how to choose these parameter values in the supplemental video 1, where the RDM-setup and LDM-setup parameters mean and , respectively.
3More precisely, we should say “semantically local” control in our context, rather than simply saying local in a geometric sense. But we loosely refer to it as local for simplicity.