To search, Click below search items.


All Published Papers Search Service


Viseme-aware realistic 3D face modeling from range images


Ken Yano, Koichi Harada


Vol. 9  No. 4  pp. 245-254


In this paper, we propose an example based realistic face modeling method with viseme control. The viseme describes the particular facial and oral positions and movements that occur alongside the voicing of phonemes. In facial animation such as speech animation and talking head, etc, a face model with open mouth is often used and the model is animated along with the speech sound by synchronizing the change of mouth shape to that of the phoneme. We claim that visemes as well as facial expressions are idiosyncratic by nature, so they have to be modeled specific to the subject to generate a truthful facial animation for the subject. The proposed method tries to automate the creation of a realistic face model with viseme control from a set of scanned data.


Face modeling, surface reconstruction, morphing