Automatic generation of head models and facial animations considering personal characteristics

Akinobu Maejima, Hiroto Yarimizu, Hiroyuki Kubo, Shigeo Morishima

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

    3 Citations (Scopus)

    Abstract

    We propose a new automatic head modeling system to generate individualized head models which can express person-specific facial expressions. The head modeling system consists of two core processes. The head modeling process with the proposed automatic mesh completion generates a whole head model only from facial range scan data. The key shape generation process generates key shapes for the generated head model based on physics-based facial muscle simulation with an individual muscle layout estimated from subject's facial expression videos. Facial animations considering personal characteristics can be synthesized using the individualized head model and key shapes. Experimental results show that the proposed system can generate head models where 84% of subjects can identify themselves. Therefore, we conclude that our head modeling system is effective to games and entertainment systems like a Future Cast System.

    Original languageEnglish
    Title of host publicationProceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST
    Pages71-78
    Number of pages8
    DOIs
    Publication statusPublished - 2010
    Event17th ACM Symposium on Virtual Reality Software and Technology, VRST 2010 - Hong Kong
    Duration: 2010 Nov 222010 Nov 24

    Other

    Other17th ACM Symposium on Virtual Reality Software and Technology, VRST 2010
    CityHong Kong
    Period10/11/2210/11/24

    Fingerprint

    Animation
    Muscle
    Physics

    Keywords

    • Automatic mesh completion
    • Facial animation synthesis
    • Facial muscle layout estimation
    • Individualized head model
    • Key shape generation

    ASJC Scopus subject areas

    • Software

    Cite this

    Maejima, A., Yarimizu, H., Kubo, H., & Morishima, S. (2010). Automatic generation of head models and facial animations considering personal characteristics. In Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST (pp. 71-78) https://doi.org/10.1145/1889863.1889875

    Automatic generation of head models and facial animations considering personal characteristics. / Maejima, Akinobu; Yarimizu, Hiroto; Kubo, Hiroyuki; Morishima, Shigeo.

    Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST. 2010. p. 71-78.

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

    Maejima, A, Yarimizu, H, Kubo, H & Morishima, S 2010, Automatic generation of head models and facial animations considering personal characteristics. in Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST. pp. 71-78, 17th ACM Symposium on Virtual Reality Software and Technology, VRST 2010, Hong Kong, 10/11/22. https://doi.org/10.1145/1889863.1889875
    Maejima A, Yarimizu H, Kubo H, Morishima S. Automatic generation of head models and facial animations considering personal characteristics. In Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST. 2010. p. 71-78 https://doi.org/10.1145/1889863.1889875
    Maejima, Akinobu ; Yarimizu, Hiroto ; Kubo, Hiroyuki ; Morishima, Shigeo. / Automatic generation of head models and facial animations considering personal characteristics. Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST. 2010. pp. 71-78
    @inproceedings{aa453c6c5e15497794efc82e0f809941,
    title = "Automatic generation of head models and facial animations considering personal characteristics",
    abstract = "We propose a new automatic head modeling system to generate individualized head models which can express person-specific facial expressions. The head modeling system consists of two core processes. The head modeling process with the proposed automatic mesh completion generates a whole head model only from facial range scan data. The key shape generation process generates key shapes for the generated head model based on physics-based facial muscle simulation with an individual muscle layout estimated from subject's facial expression videos. Facial animations considering personal characteristics can be synthesized using the individualized head model and key shapes. Experimental results show that the proposed system can generate head models where 84{\%} of subjects can identify themselves. Therefore, we conclude that our head modeling system is effective to games and entertainment systems like a Future Cast System.",
    keywords = "Automatic mesh completion, Facial animation synthesis, Facial muscle layout estimation, Individualized head model, Key shape generation",
    author = "Akinobu Maejima and Hiroto Yarimizu and Hiroyuki Kubo and Shigeo Morishima",
    year = "2010",
    doi = "10.1145/1889863.1889875",
    language = "English",
    isbn = "9781450304412",
    pages = "71--78",
    booktitle = "Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST",

    }

    TY - GEN

    T1 - Automatic generation of head models and facial animations considering personal characteristics

    AU - Maejima, Akinobu

    AU - Yarimizu, Hiroto

    AU - Kubo, Hiroyuki

    AU - Morishima, Shigeo

    PY - 2010

    Y1 - 2010

    N2 - We propose a new automatic head modeling system to generate individualized head models which can express person-specific facial expressions. The head modeling system consists of two core processes. The head modeling process with the proposed automatic mesh completion generates a whole head model only from facial range scan data. The key shape generation process generates key shapes for the generated head model based on physics-based facial muscle simulation with an individual muscle layout estimated from subject's facial expression videos. Facial animations considering personal characteristics can be synthesized using the individualized head model and key shapes. Experimental results show that the proposed system can generate head models where 84% of subjects can identify themselves. Therefore, we conclude that our head modeling system is effective to games and entertainment systems like a Future Cast System.

    AB - We propose a new automatic head modeling system to generate individualized head models which can express person-specific facial expressions. The head modeling system consists of two core processes. The head modeling process with the proposed automatic mesh completion generates a whole head model only from facial range scan data. The key shape generation process generates key shapes for the generated head model based on physics-based facial muscle simulation with an individual muscle layout estimated from subject's facial expression videos. Facial animations considering personal characteristics can be synthesized using the individualized head model and key shapes. Experimental results show that the proposed system can generate head models where 84% of subjects can identify themselves. Therefore, we conclude that our head modeling system is effective to games and entertainment systems like a Future Cast System.

    KW - Automatic mesh completion

    KW - Facial animation synthesis

    KW - Facial muscle layout estimation

    KW - Individualized head model

    KW - Key shape generation

    UR - http://www.scopus.com/inward/record.url?scp=79953062344&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=79953062344&partnerID=8YFLogxK

    U2 - 10.1145/1889863.1889875

    DO - 10.1145/1889863.1889875

    M3 - Conference contribution

    AN - SCOPUS:79953062344

    SN - 9781450304412

    SP - 71

    EP - 78

    BT - Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST

    ER -