Qasi-developable garment transfer for animals

Fumiya Narita, Shunsuke Saito, Tsukasa Fukusato, Shigeo Morishima

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

    Abstract

    In this paper, we present an interactive framework to model garments for animals from a template garment model based on correspondences between the source and the target bodies. We address two critical challenges of garment transfer across significantly different body shapes and postures (e.g., for quadruped and human); (1) ambiguity in the correspondences and (2) distortion due to large variation in scale of each body part. Our efficient cross-parameterization algorithm and intuitive user interface allow us to interactively compute correspondences and transfer the overall shape of garments. We also introduce a novel algorithm for local coordinate optimization that minimizes the distortion of transferred garments, which leads a resulting model to a quasi-developable surface and hence ready for fabrication. Finally, we demonstrate the robustness and effectiveness of our approach on a various garments and body shapes, showing that visually pleasant garment models for animals can be generated and fabricated by our system with minimal effort.

    Original languageEnglish
    Title of host publicationSIGGRAPH Asia 2017 Technical Briefs, SA 2017
    PublisherAssociation for Computing Machinery, Inc
    ISBN (Electronic)9781450354066
    DOIs
    Publication statusPublished - 2017 Nov 27
    EventSIGGRAPH Asia 2017 Technical Briefs, SA 2017 - Bangkok, Thailand
    Duration: 2017 Nov 272017 Nov 30

    Other

    OtherSIGGRAPH Asia 2017 Technical Briefs, SA 2017
    CountryThailand
    CityBangkok
    Period17/11/2717/11/30

    Fingerprint

    Animals
    Parameterization
    User interfaces
    Fabrication

    Keywords

    • Developable optimization
    • Garment modeling Interactive correspondence mapping

    ASJC Scopus subject areas

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

    Cite this

    Narita, F., Saito, S., Fukusato, T., & Morishima, S. (2017). Qasi-developable garment transfer for animals. In SIGGRAPH Asia 2017 Technical Briefs, SA 2017 [25] Association for Computing Machinery, Inc. https://doi.org/10.1145/3145749.3149441

    Qasi-developable garment transfer for animals. / Narita, Fumiya; Saito, Shunsuke; Fukusato, Tsukasa; Morishima, Shigeo.

    SIGGRAPH Asia 2017 Technical Briefs, SA 2017. Association for Computing Machinery, Inc, 2017. 25.

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

    Narita, F, Saito, S, Fukusato, T & Morishima, S 2017, Qasi-developable garment transfer for animals. in SIGGRAPH Asia 2017 Technical Briefs, SA 2017., 25, Association for Computing Machinery, Inc, SIGGRAPH Asia 2017 Technical Briefs, SA 2017, Bangkok, Thailand, 17/11/27. https://doi.org/10.1145/3145749.3149441
    Narita F, Saito S, Fukusato T, Morishima S. Qasi-developable garment transfer for animals. In SIGGRAPH Asia 2017 Technical Briefs, SA 2017. Association for Computing Machinery, Inc. 2017. 25 https://doi.org/10.1145/3145749.3149441
    Narita, Fumiya ; Saito, Shunsuke ; Fukusato, Tsukasa ; Morishima, Shigeo. / Qasi-developable garment transfer for animals. SIGGRAPH Asia 2017 Technical Briefs, SA 2017. Association for Computing Machinery, Inc, 2017.
    @inproceedings{eeb4c3612caa4e668c2071dc7d5b4b26,
    title = "Qasi-developable garment transfer for animals",
    abstract = "In this paper, we present an interactive framework to model garments for animals from a template garment model based on correspondences between the source and the target bodies. We address two critical challenges of garment transfer across significantly different body shapes and postures (e.g., for quadruped and human); (1) ambiguity in the correspondences and (2) distortion due to large variation in scale of each body part. Our efficient cross-parameterization algorithm and intuitive user interface allow us to interactively compute correspondences and transfer the overall shape of garments. We also introduce a novel algorithm for local coordinate optimization that minimizes the distortion of transferred garments, which leads a resulting model to a quasi-developable surface and hence ready for fabrication. Finally, we demonstrate the robustness and effectiveness of our approach on a various garments and body shapes, showing that visually pleasant garment models for animals can be generated and fabricated by our system with minimal effort.",
    keywords = "Developable optimization, Garment modeling Interactive correspondence mapping",
    author = "Fumiya Narita and Shunsuke Saito and Tsukasa Fukusato and Shigeo Morishima",
    year = "2017",
    month = "11",
    day = "27",
    doi = "10.1145/3145749.3149441",
    language = "English",
    booktitle = "SIGGRAPH Asia 2017 Technical Briefs, SA 2017",
    publisher = "Association for Computing Machinery, Inc",

    }

    TY - GEN

    T1 - Qasi-developable garment transfer for animals

    AU - Narita, Fumiya

    AU - Saito, Shunsuke

    AU - Fukusato, Tsukasa

    AU - Morishima, Shigeo

    PY - 2017/11/27

    Y1 - 2017/11/27

    N2 - In this paper, we present an interactive framework to model garments for animals from a template garment model based on correspondences between the source and the target bodies. We address two critical challenges of garment transfer across significantly different body shapes and postures (e.g., for quadruped and human); (1) ambiguity in the correspondences and (2) distortion due to large variation in scale of each body part. Our efficient cross-parameterization algorithm and intuitive user interface allow us to interactively compute correspondences and transfer the overall shape of garments. We also introduce a novel algorithm for local coordinate optimization that minimizes the distortion of transferred garments, which leads a resulting model to a quasi-developable surface and hence ready for fabrication. Finally, we demonstrate the robustness and effectiveness of our approach on a various garments and body shapes, showing that visually pleasant garment models for animals can be generated and fabricated by our system with minimal effort.

    AB - In this paper, we present an interactive framework to model garments for animals from a template garment model based on correspondences between the source and the target bodies. We address two critical challenges of garment transfer across significantly different body shapes and postures (e.g., for quadruped and human); (1) ambiguity in the correspondences and (2) distortion due to large variation in scale of each body part. Our efficient cross-parameterization algorithm and intuitive user interface allow us to interactively compute correspondences and transfer the overall shape of garments. We also introduce a novel algorithm for local coordinate optimization that minimizes the distortion of transferred garments, which leads a resulting model to a quasi-developable surface and hence ready for fabrication. Finally, we demonstrate the robustness and effectiveness of our approach on a various garments and body shapes, showing that visually pleasant garment models for animals can be generated and fabricated by our system with minimal effort.

    KW - Developable optimization

    KW - Garment modeling Interactive correspondence mapping

    UR - http://www.scopus.com/inward/record.url?scp=85040340903&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85040340903&partnerID=8YFLogxK

    U2 - 10.1145/3145749.3149441

    DO - 10.1145/3145749.3149441

    M3 - Conference contribution

    AN - SCOPUS:85040340903

    BT - SIGGRAPH Asia 2017 Technical Briefs, SA 2017

    PB - Association for Computing Machinery, Inc

    ER -