Automatic 3D face generation from video with sparse point constraint and dense deformable model

Tomoya Hara, Akinobu Maejima, Shigeo Morishima

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

    Abstract

    3D face models have been widely applied in various fields (e.g. biometrics, movies, video games). Especially, it is one of the most popular and challenging tasks in computer vision and computer graphics to reconstruct a 3D face model only with single camera without attaching landmarks and projecting laser dots or structured light patterns on a face. For example, Maejima proposed a method, based on generic-model approach, which can quickly reconstruct a 3D face model from 2D single photograph using a deformable face model [Maejima et al. 2008]. However, since it supposes input as a frontal face image, this method cannot express the individual facial parts' geometry such as height of nose and cheek contour accurately.

    Original languageEnglish
    Title of host publicationSIGGRAPH Asia 2011 Posters, SA'11
    DOIs
    Publication statusPublished - 2011
    EventSIGGRAPH Asia 2011 Posters, SA'11 - Hong Kong
    Duration: 2011 Dec 122011 Dec 15

    Other

    OtherSIGGRAPH Asia 2011 Posters, SA'11
    CityHong Kong
    Period11/12/1211/12/15

    Fingerprint

    Computer graphics
    Biometrics
    Computer vision
    Cameras
    Geometry
    Lasers

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Computer Vision and Pattern Recognition

    Cite this

    Automatic 3D face generation from video with sparse point constraint and dense deformable model. / Hara, Tomoya; Maejima, Akinobu; Morishima, Shigeo.

    SIGGRAPH Asia 2011 Posters, SA'11. 2011. 18.

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

    Hara, T, Maejima, A & Morishima, S 2011, Automatic 3D face generation from video with sparse point constraint and dense deformable model. in SIGGRAPH Asia 2011 Posters, SA'11., 18, SIGGRAPH Asia 2011 Posters, SA'11, Hong Kong, 11/12/12. https://doi.org/10.1145/2073304.2073323
    Hara, Tomoya ; Maejima, Akinobu ; Morishima, Shigeo. / Automatic 3D face generation from video with sparse point constraint and dense deformable model. SIGGRAPH Asia 2011 Posters, SA'11. 2011.
    @inproceedings{f37192f1ed8943f790c03b47bbb99e3e,
    title = "Automatic 3D face generation from video with sparse point constraint and dense deformable model",
    abstract = "3D face models have been widely applied in various fields (e.g. biometrics, movies, video games). Especially, it is one of the most popular and challenging tasks in computer vision and computer graphics to reconstruct a 3D face model only with single camera without attaching landmarks and projecting laser dots or structured light patterns on a face. For example, Maejima proposed a method, based on generic-model approach, which can quickly reconstruct a 3D face model from 2D single photograph using a deformable face model [Maejima et al. 2008]. However, since it supposes input as a frontal face image, this method cannot express the individual facial parts' geometry such as height of nose and cheek contour accurately.",
    author = "Tomoya Hara and Akinobu Maejima and Shigeo Morishima",
    year = "2011",
    doi = "10.1145/2073304.2073323",
    language = "English",
    isbn = "9781450311373",
    booktitle = "SIGGRAPH Asia 2011 Posters, SA'11",

    }

    TY - GEN

    T1 - Automatic 3D face generation from video with sparse point constraint and dense deformable model

    AU - Hara, Tomoya

    AU - Maejima, Akinobu

    AU - Morishima, Shigeo

    PY - 2011

    Y1 - 2011

    N2 - 3D face models have been widely applied in various fields (e.g. biometrics, movies, video games). Especially, it is one of the most popular and challenging tasks in computer vision and computer graphics to reconstruct a 3D face model only with single camera without attaching landmarks and projecting laser dots or structured light patterns on a face. For example, Maejima proposed a method, based on generic-model approach, which can quickly reconstruct a 3D face model from 2D single photograph using a deformable face model [Maejima et al. 2008]. However, since it supposes input as a frontal face image, this method cannot express the individual facial parts' geometry such as height of nose and cheek contour accurately.

    AB - 3D face models have been widely applied in various fields (e.g. biometrics, movies, video games). Especially, it is one of the most popular and challenging tasks in computer vision and computer graphics to reconstruct a 3D face model only with single camera without attaching landmarks and projecting laser dots or structured light patterns on a face. For example, Maejima proposed a method, based on generic-model approach, which can quickly reconstruct a 3D face model from 2D single photograph using a deformable face model [Maejima et al. 2008]. However, since it supposes input as a frontal face image, this method cannot express the individual facial parts' geometry such as height of nose and cheek contour accurately.

    UR - http://www.scopus.com/inward/record.url?scp=84855484391&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84855484391&partnerID=8YFLogxK

    U2 - 10.1145/2073304.2073323

    DO - 10.1145/2073304.2073323

    M3 - Conference contribution

    AN - SCOPUS:84855484391

    SN - 9781450311373

    BT - SIGGRAPH Asia 2011 Posters, SA'11

    ER -