Face Modeling and Animation Language for MPEG-4 XMT Framework

Abstract

Abstract-This paper proposes FML, an XML-based face modeling and animation language. FML provides a structured content description method for multimedia presentations based on face animation. The language can be used as direct input to compatible players, or be compiled within MPEG-4 XMT framework to create MPEG-4 presentations. The language allows parallel and sequential action description, decision-making and dynamic event-based scenarios, model configuration, and behavioral template definition. Facial actions include talking, expressions, head movements, and low-level MPEG-4 FAPs. The ShowFace and iFACE animation frameworks are also reviewed as example FML-based animation systems.

An extensible framework for interactive facial animation with facial expressions, lip synchronization and eye behavior

“…However, these standards provide a rather low-level basis for animators, as they describe the parameters as a set of "pseudo-muscles" that can be activated in a given moment to produce a facial expression (Section 3.3 overviews the MPEG-4 FA). Hence there have been several efforts made to produce a higher-level parameter approach to generate facial animations in an effective way [Perlin 1997;Cassell et al 2001;Rutledge 2001;Byun and Badler 2002;Carolis et al 2004;Not et al 2005;Arya and DiPaola 2007].…”

“…Recent research on facial animation has lead to models that explore expressiveness, communication, and interactivity; much of this research is focused on ECA development [de Rosis et al 2003;Smid et al 2004;Cosi et al 2007;Huang et al 2008] and provides a range of studies that correlate human psycho-social behavior and facial animation. Together with development of a facial animation platform, we found several studies about face parameterization and scripting languages for assisted and automatic animation generation [Perlin 1997;Cassell et al 2001;Rutledge 2001;Arafa and Mamdani 2002;Byun and Badler 2002;Carolis et al 2004;Not et al 2005;Arya and DiPaola 2007;Vilhjálmsson et al 2007]. These studies have enabled higher-level description of a character's facial behavior.…”