Animation of synthetic faces in MPEG-4

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

External Research Organisations

  • AT&T Labs
View graph of relations

Details

Original languageEnglish
Title of host publicationProceedings
Subtitle of host publicationComputer Animation, CA 1998
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages49-55
Number of pages7
ISBN (print)9780818685415
Publication statusPublished - 1998
Externally publishedYes
Event1998 Computer Animation, CA 1998 - Philadelphia, United States
Duration: 8 Jun 199810 Jun 1998

Abstract

MPEG-4 is the first international standard that standardizes true multimedia communication-including natural and synthetic audio, natural and synthetic video, as well as 3D graphics. Integrated into this standard is the capability to define and animate virtual humans consisting of synthetic heads and bodies. For the head, more than 70 model-independent animation parameters defining low-level actions like «move left mouth corner» up to high-level parameters like facial expressions and visemes are standardized In a communication application. The encoder can define the face model using MPEG-4 BIFS (BInary Format for Scenes) and transmit it to the decoder. Alternatively, the encoder can rely on a face model that is available at the decoder. The animation parameters are quantized, predictively encoded using an arithmetic encoder or a DCT. The decoder receives the model and the animation parameters in order to animate the model. Since MPEG-4 defines the minimum MPEG-4 terminal capabilities in profiles and levels, the encoder knows the quality of the animation at the decoder.

ASJC Scopus subject areas

Cite this

Animation of synthetic faces in MPEG-4. / Ostermann, Jörn.
Proceedings : Computer Animation, CA 1998. Institute of Electrical and Electronics Engineers Inc., 1998. p. 49-55 681907.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Ostermann, J 1998, Animation of synthetic faces in MPEG-4. in Proceedings : Computer Animation, CA 1998., 681907, Institute of Electrical and Electronics Engineers Inc., pp. 49-55, 1998 Computer Animation, CA 1998, Philadelphia, United States, 8 Jun 1998. https://doi.org/10.1109/CA.1998.681907
Ostermann, J. (1998). Animation of synthetic faces in MPEG-4. In Proceedings : Computer Animation, CA 1998 (pp. 49-55). Article 681907 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CA.1998.681907
Ostermann J. Animation of synthetic faces in MPEG-4. In Proceedings : Computer Animation, CA 1998. Institute of Electrical and Electronics Engineers Inc. 1998. p. 49-55. 681907 doi: 10.1109/CA.1998.681907
Ostermann, Jörn. / Animation of synthetic faces in MPEG-4. Proceedings : Computer Animation, CA 1998. Institute of Electrical and Electronics Engineers Inc., 1998. pp. 49-55
Download
@inproceedings{97e94ef532134addb7bbc671e377480f,
title = "Animation of synthetic faces in MPEG-4",
abstract = "MPEG-4 is the first international standard that standardizes true multimedia communication-including natural and synthetic audio, natural and synthetic video, as well as 3D graphics. Integrated into this standard is the capability to define and animate virtual humans consisting of synthetic heads and bodies. For the head, more than 70 model-independent animation parameters defining low-level actions like «move left mouth corner» up to high-level parameters like facial expressions and visemes are standardized In a communication application. The encoder can define the face model using MPEG-4 BIFS (BInary Format for Scenes) and transmit it to the decoder. Alternatively, the encoder can rely on a face model that is available at the decoder. The animation parameters are quantized, predictively encoded using an arithmetic encoder or a DCT. The decoder receives the model and the animation parameters in order to animate the model. Since MPEG-4 defines the minimum MPEG-4 terminal capabilities in profiles and levels, the encoder knows the quality of the animation at the decoder.",
author = "J{\"o}rn Ostermann",
note = "Publisher Copyright: {\textcopyright} 1998 IEEE.; 1998 Computer Animation, CA 1998 ; Conference date: 08-06-1998 Through 10-06-1998",
year = "1998",
doi = "10.1109/CA.1998.681907",
language = "English",
isbn = "9780818685415",
pages = "49--55",
booktitle = "Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Download

TY - GEN

T1 - Animation of synthetic faces in MPEG-4

AU - Ostermann, Jörn

N1 - Publisher Copyright: © 1998 IEEE.

PY - 1998

Y1 - 1998

N2 - MPEG-4 is the first international standard that standardizes true multimedia communication-including natural and synthetic audio, natural and synthetic video, as well as 3D graphics. Integrated into this standard is the capability to define and animate virtual humans consisting of synthetic heads and bodies. For the head, more than 70 model-independent animation parameters defining low-level actions like «move left mouth corner» up to high-level parameters like facial expressions and visemes are standardized In a communication application. The encoder can define the face model using MPEG-4 BIFS (BInary Format for Scenes) and transmit it to the decoder. Alternatively, the encoder can rely on a face model that is available at the decoder. The animation parameters are quantized, predictively encoded using an arithmetic encoder or a DCT. The decoder receives the model and the animation parameters in order to animate the model. Since MPEG-4 defines the minimum MPEG-4 terminal capabilities in profiles and levels, the encoder knows the quality of the animation at the decoder.

AB - MPEG-4 is the first international standard that standardizes true multimedia communication-including natural and synthetic audio, natural and synthetic video, as well as 3D graphics. Integrated into this standard is the capability to define and animate virtual humans consisting of synthetic heads and bodies. For the head, more than 70 model-independent animation parameters defining low-level actions like «move left mouth corner» up to high-level parameters like facial expressions and visemes are standardized In a communication application. The encoder can define the face model using MPEG-4 BIFS (BInary Format for Scenes) and transmit it to the decoder. Alternatively, the encoder can rely on a face model that is available at the decoder. The animation parameters are quantized, predictively encoded using an arithmetic encoder or a DCT. The decoder receives the model and the animation parameters in order to animate the model. Since MPEG-4 defines the minimum MPEG-4 terminal capabilities in profiles and levels, the encoder knows the quality of the animation at the decoder.

UR - http://www.scopus.com/inward/record.url?scp=84962695927&partnerID=8YFLogxK

U2 - 10.1109/CA.1998.681907

DO - 10.1109/CA.1998.681907

M3 - Conference contribution

AN - SCOPUS:84962695927

SN - 9780818685415

SP - 49

EP - 55

BT - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1998 Computer Animation, CA 1998

Y2 - 8 June 1998 through 10 June 1998

ER -

By the same author(s)