AvPM: an avatar-based personal messenger for low bandwidth networks

Authors:
Yu-En Wu;Cheng-Chin Chiang
Affiliations:
Department of Computer Science & Information Engineering, National Dong Hwa University, Shoufeng, Hualien, Taiwan;Department of Computer Science & Information Engineering, National Dong Hwa University, Shoufeng, Hualien, Taiwan
Venue:
GPC'10 Proceedings of the 5th international conference on Advances in Grid and Pervasive Computing
Year:
2010

Citing 4
Cited 0

Active Appearance Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Exms: an animated and avatar-based messaging system for expressive peer communication

GROUP '03 Proceedings of the 2003 international ACM SIGGROUP conference on Supporting group work
Active Appearance Models Revisited

International Journal of Computer Vision
Overview of the H.264/AVC video coding standard

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents the novel design of an avatar-based personal messenger called the AvPM Differing a lot from the common messengers like Microsoft MSN and Yahoo Messenger, the proposed AvPM allows the receiving site to synthesize on the fly a virtual avatar having the synchronized voices, facial expressions and head poses of the speaker at the speaking site More importantly, the visual data transmitted by the AvPM is not a large volume of compressed video of the speaker's appearance, but a small amount of synthesizing parameters for rendering the synchronized avatar's appearance This novel feature makes the AvPM very suitable for personal audio-visual communication over low-bandwidth networks The experimental results show that the AvPM outperforms the MSN and H.264 in terms of the required network bandwidth and the rendered audio-visual quality.