Facial animation reflecting personal characteristics by automatic head modeling and facial muscle adjustment

Akinobu Maejima, Hiroyuki Kubo, Shigeo Morishima

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    We propose a new automatic character modeling system which can generate an individualized head model only from a facial range scan data and an individualized facial animation with expression change. The head modeling system consists of two core modules: the head modeling module which can generate a head model from a personal facial range scan data using automatic mesh completion, and the key shape generation module which can generate key shapes for the generated head model based on physics-based facial muscle simulation with a personal muscle layout estimated from subject's facial expression videos. As a result, we can generate a head model which can synthesize facial expressions and impression similar to the target person. The experimental result shows that we archive to synthesize CG characters that subjects can identify themselves with 84%. Therefore, we conclude that our head modeling system is effective to games and entertainment systems like the Future Cast.

    Original languageEnglish
    Title of host publicationISCIT 2010 - 2010 10th International Symposium on Communications and Information Technologies
    Pages7-12
    Number of pages6
    DOIs
    Publication statusPublished - 2010
    Event2010 10th International Symposium on Communications and Information Technologies, ISCIT 2010 - Tokyo
    Duration: 2010 Oct 262010 Oct 29

    Other

    Other2010 10th International Symposium on Communications and Information Technologies, ISCIT 2010
    CityTokyo
    Period10/10/2610/10/29

    Fingerprint

    Animation
    Muscle
    Physics

    ASJC Scopus subject areas

    • Computer Networks and Communications
    • Information Systems

    Cite this

    Maejima, A., Kubo, H., & Morishima, S. (2010). Facial animation reflecting personal characteristics by automatic head modeling and facial muscle adjustment. In ISCIT 2010 - 2010 10th International Symposium on Communications and Information Technologies (pp. 7-12). [5664922] https://doi.org/10.1109/ISCIT.2010.5664922

    Facial animation reflecting personal characteristics by automatic head modeling and facial muscle adjustment. / Maejima, Akinobu; Kubo, Hiroyuki; Morishima, Shigeo.

    ISCIT 2010 - 2010 10th International Symposium on Communications and Information Technologies. 2010. p. 7-12 5664922.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Maejima, A, Kubo, H & Morishima, S 2010, Facial animation reflecting personal characteristics by automatic head modeling and facial muscle adjustment. in ISCIT 2010 - 2010 10th International Symposium on Communications and Information Technologies., 5664922, pp. 7-12, 2010 10th International Symposium on Communications and Information Technologies, ISCIT 2010, Tokyo, 10/10/26. https://doi.org/10.1109/ISCIT.2010.5664922
    Maejima A, Kubo H, Morishima S. Facial animation reflecting personal characteristics by automatic head modeling and facial muscle adjustment. In ISCIT 2010 - 2010 10th International Symposium on Communications and Information Technologies. 2010. p. 7-12. 5664922 https://doi.org/10.1109/ISCIT.2010.5664922
    Maejima, Akinobu ; Kubo, Hiroyuki ; Morishima, Shigeo. / Facial animation reflecting personal characteristics by automatic head modeling and facial muscle adjustment. ISCIT 2010 - 2010 10th International Symposium on Communications and Information Technologies. 2010. pp. 7-12
    @inproceedings{eed87dc2b4a647cb816019a1f145c2a8,
    title = "Facial animation reflecting personal characteristics by automatic head modeling and facial muscle adjustment",
    abstract = "We propose a new automatic character modeling system which can generate an individualized head model only from a facial range scan data and an individualized facial animation with expression change. The head modeling system consists of two core modules: the head modeling module which can generate a head model from a personal facial range scan data using automatic mesh completion, and the key shape generation module which can generate key shapes for the generated head model based on physics-based facial muscle simulation with a personal muscle layout estimated from subject's facial expression videos. As a result, we can generate a head model which can synthesize facial expressions and impression similar to the target person. The experimental result shows that we archive to synthesize CG characters that subjects can identify themselves with 84{\%}. Therefore, we conclude that our head modeling system is effective to games and entertainment systems like the Future Cast.",
    author = "Akinobu Maejima and Hiroyuki Kubo and Shigeo Morishima",
    year = "2010",
    doi = "10.1109/ISCIT.2010.5664922",
    language = "English",
    isbn = "9781424470105",
    pages = "7--12",
    booktitle = "ISCIT 2010 - 2010 10th International Symposium on Communications and Information Technologies",

    }

    TY - GEN

    T1 - Facial animation reflecting personal characteristics by automatic head modeling and facial muscle adjustment

    AU - Maejima, Akinobu

    AU - Kubo, Hiroyuki

    AU - Morishima, Shigeo

    PY - 2010

    Y1 - 2010

    N2 - We propose a new automatic character modeling system which can generate an individualized head model only from a facial range scan data and an individualized facial animation with expression change. The head modeling system consists of two core modules: the head modeling module which can generate a head model from a personal facial range scan data using automatic mesh completion, and the key shape generation module which can generate key shapes for the generated head model based on physics-based facial muscle simulation with a personal muscle layout estimated from subject's facial expression videos. As a result, we can generate a head model which can synthesize facial expressions and impression similar to the target person. The experimental result shows that we archive to synthesize CG characters that subjects can identify themselves with 84%. Therefore, we conclude that our head modeling system is effective to games and entertainment systems like the Future Cast.

    AB - We propose a new automatic character modeling system which can generate an individualized head model only from a facial range scan data and an individualized facial animation with expression change. The head modeling system consists of two core modules: the head modeling module which can generate a head model from a personal facial range scan data using automatic mesh completion, and the key shape generation module which can generate key shapes for the generated head model based on physics-based facial muscle simulation with a personal muscle layout estimated from subject's facial expression videos. As a result, we can generate a head model which can synthesize facial expressions and impression similar to the target person. The experimental result shows that we archive to synthesize CG characters that subjects can identify themselves with 84%. Therefore, we conclude that our head modeling system is effective to games and entertainment systems like the Future Cast.

    UR - http://www.scopus.com/inward/record.url?scp=78651262015&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=78651262015&partnerID=8YFLogxK

    U2 - 10.1109/ISCIT.2010.5664922

    DO - 10.1109/ISCIT.2010.5664922

    M3 - Conference contribution

    SN - 9781424470105

    SP - 7

    EP - 12

    BT - ISCIT 2010 - 2010 10th International Symposium on Communications and Information Technologies

    ER -