Human head modeling based on fast-automatic mesh completion

Akinobu Maejima, Shigeo Morishima

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

    2 Citations (Scopus)

    Abstract

    The need to rapidly create 3D human head models is still an important issue in game and film production. Blanz et al have developed a morphable model which can semi-automatically reconstruct the facial appearance (3D shape and texture) and simulated hairstyles of "new" faces (faces not yet scanned into an existing database) using photographs taken from the front or other angles [Blanz et al. 2004]. However, this method still requires manual marker specification and approximately 4 minutes of computational time. Moreover, the facial reconstruction produced by this system is not accurate unless a database containing a large variety of facial models is available. We have developed a system that can rapidly generate human head models using only frontal facial range scan data. Where it is impossible to measure the 3D geometry accurately (as with hair regions) the missing data is complemented using the 3D geometry of the template mesh (TM). Our main contribution is to achieve the fast mesh completion for the head modeling based on the "Automatic Marker Setting" and the "Optimized Local Affine Transform (OLAT)". The proposed system generates a head model in approximately 8 seconds. Therefore, if users utilize a range scanner which can quickly produce range data, it is possible to generate a complete 3D head model in one minute using our system on a PC.

    Original languageEnglish
    Title of host publicationACM SIGGRAPH ASIA 2009 Posters, SIGGRAPH ASIA '09
    DOIs
    Publication statusPublished - 2009
    EventACM SIGGRAPH ASIA 2009 Posters, SIGGRAPH ASIA '09 - Yokohama
    Duration: 2009 Dec 162009 Dec 19

    Other

    OtherACM SIGGRAPH ASIA 2009 Posters, SIGGRAPH ASIA '09
    CityYokohama
    Period09/12/1609/12/19

    Fingerprint

    Affine transforms
    Geometry
    Textures
    Specifications

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Human-Computer Interaction
    • Software

    Cite this

    Maejima, A., & Morishima, S. (2009). Human head modeling based on fast-automatic mesh completion. In ACM SIGGRAPH ASIA 2009 Posters, SIGGRAPH ASIA '09 [1666831] https://doi.org/10.1145/1666778.1666831

    Human head modeling based on fast-automatic mesh completion. / Maejima, Akinobu; Morishima, Shigeo.

    ACM SIGGRAPH ASIA 2009 Posters, SIGGRAPH ASIA '09. 2009. 1666831.

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

    Maejima, A & Morishima, S 2009, Human head modeling based on fast-automatic mesh completion. in ACM SIGGRAPH ASIA 2009 Posters, SIGGRAPH ASIA '09., 1666831, ACM SIGGRAPH ASIA 2009 Posters, SIGGRAPH ASIA '09, Yokohama, 09/12/16. https://doi.org/10.1145/1666778.1666831
    Maejima A, Morishima S. Human head modeling based on fast-automatic mesh completion. In ACM SIGGRAPH ASIA 2009 Posters, SIGGRAPH ASIA '09. 2009. 1666831 https://doi.org/10.1145/1666778.1666831
    Maejima, Akinobu ; Morishima, Shigeo. / Human head modeling based on fast-automatic mesh completion. ACM SIGGRAPH ASIA 2009 Posters, SIGGRAPH ASIA '09. 2009.
    @inproceedings{971f7499bf3745b6826354be70d9f8e9,
    title = "Human head modeling based on fast-automatic mesh completion",
    abstract = "The need to rapidly create 3D human head models is still an important issue in game and film production. Blanz et al have developed a morphable model which can semi-automatically reconstruct the facial appearance (3D shape and texture) and simulated hairstyles of {"}new{"} faces (faces not yet scanned into an existing database) using photographs taken from the front or other angles [Blanz et al. 2004]. However, this method still requires manual marker specification and approximately 4 minutes of computational time. Moreover, the facial reconstruction produced by this system is not accurate unless a database containing a large variety of facial models is available. We have developed a system that can rapidly generate human head models using only frontal facial range scan data. Where it is impossible to measure the 3D geometry accurately (as with hair regions) the missing data is complemented using the 3D geometry of the template mesh (TM). Our main contribution is to achieve the fast mesh completion for the head modeling based on the {"}Automatic Marker Setting{"} and the {"}Optimized Local Affine Transform (OLAT){"}. The proposed system generates a head model in approximately 8 seconds. Therefore, if users utilize a range scanner which can quickly produce range data, it is possible to generate a complete 3D head model in one minute using our system on a PC.",
    author = "Akinobu Maejima and Shigeo Morishima",
    year = "2009",
    doi = "10.1145/1666778.1666831",
    language = "English",
    isbn = "9781605588582",
    booktitle = "ACM SIGGRAPH ASIA 2009 Posters, SIGGRAPH ASIA '09",

    }

    TY - GEN

    T1 - Human head modeling based on fast-automatic mesh completion

    AU - Maejima, Akinobu

    AU - Morishima, Shigeo

    PY - 2009

    Y1 - 2009

    N2 - The need to rapidly create 3D human head models is still an important issue in game and film production. Blanz et al have developed a morphable model which can semi-automatically reconstruct the facial appearance (3D shape and texture) and simulated hairstyles of "new" faces (faces not yet scanned into an existing database) using photographs taken from the front or other angles [Blanz et al. 2004]. However, this method still requires manual marker specification and approximately 4 minutes of computational time. Moreover, the facial reconstruction produced by this system is not accurate unless a database containing a large variety of facial models is available. We have developed a system that can rapidly generate human head models using only frontal facial range scan data. Where it is impossible to measure the 3D geometry accurately (as with hair regions) the missing data is complemented using the 3D geometry of the template mesh (TM). Our main contribution is to achieve the fast mesh completion for the head modeling based on the "Automatic Marker Setting" and the "Optimized Local Affine Transform (OLAT)". The proposed system generates a head model in approximately 8 seconds. Therefore, if users utilize a range scanner which can quickly produce range data, it is possible to generate a complete 3D head model in one minute using our system on a PC.

    AB - The need to rapidly create 3D human head models is still an important issue in game and film production. Blanz et al have developed a morphable model which can semi-automatically reconstruct the facial appearance (3D shape and texture) and simulated hairstyles of "new" faces (faces not yet scanned into an existing database) using photographs taken from the front or other angles [Blanz et al. 2004]. However, this method still requires manual marker specification and approximately 4 minutes of computational time. Moreover, the facial reconstruction produced by this system is not accurate unless a database containing a large variety of facial models is available. We have developed a system that can rapidly generate human head models using only frontal facial range scan data. Where it is impossible to measure the 3D geometry accurately (as with hair regions) the missing data is complemented using the 3D geometry of the template mesh (TM). Our main contribution is to achieve the fast mesh completion for the head modeling based on the "Automatic Marker Setting" and the "Optimized Local Affine Transform (OLAT)". The proposed system generates a head model in approximately 8 seconds. Therefore, if users utilize a range scanner which can quickly produce range data, it is possible to generate a complete 3D head model in one minute using our system on a PC.

    UR - http://www.scopus.com/inward/record.url?scp=77049116325&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77049116325&partnerID=8YFLogxK

    U2 - 10.1145/1666778.1666831

    DO - 10.1145/1666778.1666831

    M3 - Conference contribution

    SN - 9781605588582

    BT - ACM SIGGRAPH ASIA 2009 Posters, SIGGRAPH ASIA '09

    ER -