Face texture synthesis from multiple images via sparse and dense correspondence

Shugo Yamaguchi, Shigeo Morishima

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

    2 Citations (Scopus)

    Abstract

    We have a desire to edit images for various purposes such as art, entertainment, and film production so texture synthesis methods have been proposed. Especially, PatchMatch algorithm [Barnes et al. 2009] enabled us to easily use many image editing tools. However, these tools are applied to one image. If we can automatically synthesize from various examples, we can create new and higher quality images. Visio-lization [Mohammed et al. 2009] generated average face by synthesis of face image database. However, the synthesis was applied block-wise so there were artifacts on the result and free form features of source images such as wrinkles could not be preserved. We proposed a new synthesis method for multiple images. We applied sparse and dense nearest neighbor search so that we can preserve both input and source database image features. Our method allows us to create a novel image from a number of examples.

    Original languageEnglish
    Title of host publicationSA 2016 - SIGGRAPH ASIA 2016 Technical Briefs
    PublisherAssociation for Computing Machinery, Inc
    ISBN (Electronic)9781450345415
    DOIs
    Publication statusPublished - 2016 Nov 28
    Event2016 SIGGRAPH ASIA Technical Briefs, SA 2016 - Macau, China
    Duration: 2016 Dec 52016 Dec 8

    Other

    Other2016 SIGGRAPH ASIA Technical Briefs, SA 2016
    CountryChina
    CityMacau
    Period16/12/516/12/8

    Fingerprint

    Textures
    Image quality

    Keywords

    • PatchMatch
    • Texture synthesis
    • Visio-lization

    ASJC Scopus subject areas

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

    Cite this

    Yamaguchi, S., & Morishima, S. (2016). Face texture synthesis from multiple images via sparse and dense correspondence. In SA 2016 - SIGGRAPH ASIA 2016 Technical Briefs [a14] Association for Computing Machinery, Inc. https://doi.org/10.1145/3005358.3005386

    Face texture synthesis from multiple images via sparse and dense correspondence. / Yamaguchi, Shugo; Morishima, Shigeo.

    SA 2016 - SIGGRAPH ASIA 2016 Technical Briefs. Association for Computing Machinery, Inc, 2016. a14.

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

    Yamaguchi, S & Morishima, S 2016, Face texture synthesis from multiple images via sparse and dense correspondence. in SA 2016 - SIGGRAPH ASIA 2016 Technical Briefs., a14, Association for Computing Machinery, Inc, 2016 SIGGRAPH ASIA Technical Briefs, SA 2016, Macau, China, 16/12/5. https://doi.org/10.1145/3005358.3005386
    Yamaguchi S, Morishima S. Face texture synthesis from multiple images via sparse and dense correspondence. In SA 2016 - SIGGRAPH ASIA 2016 Technical Briefs. Association for Computing Machinery, Inc. 2016. a14 https://doi.org/10.1145/3005358.3005386
    Yamaguchi, Shugo ; Morishima, Shigeo. / Face texture synthesis from multiple images via sparse and dense correspondence. SA 2016 - SIGGRAPH ASIA 2016 Technical Briefs. Association for Computing Machinery, Inc, 2016.
    @inproceedings{2583fc8dafde4b219cc33d88052e822e,
    title = "Face texture synthesis from multiple images via sparse and dense correspondence",
    abstract = "We have a desire to edit images for various purposes such as art, entertainment, and film production so texture synthesis methods have been proposed. Especially, PatchMatch algorithm [Barnes et al. 2009] enabled us to easily use many image editing tools. However, these tools are applied to one image. If we can automatically synthesize from various examples, we can create new and higher quality images. Visio-lization [Mohammed et al. 2009] generated average face by synthesis of face image database. However, the synthesis was applied block-wise so there were artifacts on the result and free form features of source images such as wrinkles could not be preserved. We proposed a new synthesis method for multiple images. We applied sparse and dense nearest neighbor search so that we can preserve both input and source database image features. Our method allows us to create a novel image from a number of examples.",
    keywords = "PatchMatch, Texture synthesis, Visio-lization",
    author = "Shugo Yamaguchi and Shigeo Morishima",
    year = "2016",
    month = "11",
    day = "28",
    doi = "10.1145/3005358.3005386",
    language = "English",
    booktitle = "SA 2016 - SIGGRAPH ASIA 2016 Technical Briefs",
    publisher = "Association for Computing Machinery, Inc",

    }

    TY - GEN

    T1 - Face texture synthesis from multiple images via sparse and dense correspondence

    AU - Yamaguchi, Shugo

    AU - Morishima, Shigeo

    PY - 2016/11/28

    Y1 - 2016/11/28

    N2 - We have a desire to edit images for various purposes such as art, entertainment, and film production so texture synthesis methods have been proposed. Especially, PatchMatch algorithm [Barnes et al. 2009] enabled us to easily use many image editing tools. However, these tools are applied to one image. If we can automatically synthesize from various examples, we can create new and higher quality images. Visio-lization [Mohammed et al. 2009] generated average face by synthesis of face image database. However, the synthesis was applied block-wise so there were artifacts on the result and free form features of source images such as wrinkles could not be preserved. We proposed a new synthesis method for multiple images. We applied sparse and dense nearest neighbor search so that we can preserve both input and source database image features. Our method allows us to create a novel image from a number of examples.

    AB - We have a desire to edit images for various purposes such as art, entertainment, and film production so texture synthesis methods have been proposed. Especially, PatchMatch algorithm [Barnes et al. 2009] enabled us to easily use many image editing tools. However, these tools are applied to one image. If we can automatically synthesize from various examples, we can create new and higher quality images. Visio-lization [Mohammed et al. 2009] generated average face by synthesis of face image database. However, the synthesis was applied block-wise so there were artifacts on the result and free form features of source images such as wrinkles could not be preserved. We proposed a new synthesis method for multiple images. We applied sparse and dense nearest neighbor search so that we can preserve both input and source database image features. Our method allows us to create a novel image from a number of examples.

    KW - PatchMatch

    KW - Texture synthesis

    KW - Visio-lization

    UR - http://www.scopus.com/inward/record.url?scp=85008260067&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85008260067&partnerID=8YFLogxK

    U2 - 10.1145/3005358.3005386

    DO - 10.1145/3005358.3005386

    M3 - Conference contribution

    AN - SCOPUS:85008260067

    BT - SA 2016 - SIGGRAPH ASIA 2016 Technical Briefs

    PB - Association for Computing Machinery, Inc

    ER -