We present a novel technique for creating realistic facial animations given a small number of real images and a few parameters for the in-between images. This scheme can also be used for reconstructing facial movies where the parameters can be automatically extracted from the images. The in-between images are produced without ever generating a three-dimensional model of the face. Since facial motion due to expressions are not well defined mathematically our approach is based on utilizing image patterns in facial motion. These patterns were revealed by an empirical study which analyzed and compared image motion patterns in facial expressions. The major contribution of this work is showing how parameterized “ideal” motion templates can generate facial movies for different people and different expressions, where the parameters are extracted automatically from the image sequence. To test the quality of the algorithm, image sequences (one of which was taken from a TV news broadcast) were reconstructed, yielding movies hardly distinguishable from the originals.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Published online: 2 October 2002
Correspondence to: A. Tal
Work has been supported in part by the Israeli Ministry of Industry and Trade, The MOST Consortium
Rights and permissions
About this article
Cite this article
Moiza, G., Tal, A., Shimshoni, I. et al. Image-based animation of facial expressions. Visual Comp 18, 445–467 (2002). https://doi.org/10.1007/s003710100157
Issue Date:
DOI: https://doi.org/10.1007/s003710100157