Abstract
This paper presents a hybrid method for synthesizing natural animation of facial expression with data from motion capture. The captured expression was transferred from the space of source performance to that of a 3D target face using an accurate mapping process in order to realize the reuse of motion data. The transferred animation was then applied to synthesize the expression of the target model through a framework of two-stage deformation. A local deformation technique preliminarily considered a set of neighbor feature points for every vertex and their impact on the vertex. Furthermore, the global deformation was exploited to ensure the smoothness of the whole facial mesh. The experimental results show our hybrid mesh deformation strategy was effective, which could animate different target face without complicated manual efforts required by most of facial animation approaches. DOI: http://dx.doi.org/10.11591/telkomnika.v11i3.2039
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: TELKOMNIKA Indonesian Journal of Electrical Engineering
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
