Animated Talking Head with Personalized 3D Head Model

Authors:
Jörn Ostermann;Lawrence S. Chen;Thomas S. Huang
Affiliations:
AT&T Labs—Research, Room 3-231, 100 Schultz Dr., Red Bank, NJ, 07701;Beckman Institute CSL, University of Urbana, IL 61801;Beckman Institute CSL, University of Urbana, IL 61801
Venue:
Journal of VLSI Signal Processing Systems - special issue on multimedia signal processing
Year:
1998

Citing 4
Cited 1

Realistic modeling for facial animation

SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Automatic Creation of 3D Facial Models

IEEE Computer Graphics and Applications
Automatic 3D Cloning and Real-Time Animation of a Human Face

CA '97 Proceedings of the Computer Animation
Speech dialogue with facial displays: multimodal human-computer conversation

ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics

EDFCES: a new example-driven 3D face construction and editing system

Machine Graphics & Vision International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Natural Human-Computer Interface requires integrationof realistic audio and visual information forperception and display. An example of such an interface is ananimated talking head displayed on the computer screen in theform of a human-like computer agent. This system converts textto acoustic speech with synchronized animation of mouthmovements. The talking head is based on a generic 3D human headmodel, but to improve realism, natural looking personalizedmodels are necessary. In this paper, we report a semi-automaticmethod for adapting a generic head model to 3D range data of ahuman head obtained from a 3D-laser range scanner. Thispersonalized model is incorporated into the talking head system. With texture mapping, the personalized model offers a morenatural and realistic look than the generic model. The modelcreated with the proposed method compares favorable to genericmodels.