BG maker: Example-based anime background image creation from a photograph

Shugo Yamaguchi, Chie Furusawa, Takuya Kato, Tsukasa Fukusato, Shigeo Morishima

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

    1 Citation (Scopus)

    Abstract

    Anime designers often paint actual sceneries to serve as background images based on photographs to complement characters. As paint- ing background scenery is time consuming and cost ineffective, there is a high demand for techniques that can convert photographs into anime styled graphics. Previous approaches for this purpose, such as Image Quilting [Efros and Freeman 2001] transferred a source texture onto a target photograph. These methods synthesized corresponding source patches with the target elements in a photo- graph, and correspondence was achieved through nearest-neighbor search such as PatchMatch [Barnes et al. 2009]. However, the near- est-neighbor patch is not always the most suitable patch for anime transfer because photographs and anime background images differ in color and texture. For example, real-world color need to be con- verted into specific colors for anime; further, the type of brushwork required to realize an anime effect, is different for different photo- graph elements (e.g. sky, mountain, grass). Thus, to get the most suitable patch, we propose a method, wherein we establish global region correspondence before local patch match. In our proposed method, BGMaker, (1) we divide the real and anime images into re- gions; (2) then, we automatically acquire correspondence between each region on the basis of color and texture features, and (3) search and synthesize the most suitable patch within the corresponding re- gion. Our primary contribution in this paper is a method for au- Tomatically acquiring correspondence between target regions and source regions of different color and texture, which allows us to generate an anime background image while preserving the details of the source image.

    Original languageEnglish
    Title of host publicationACM SIGGRAPH 2015 Posters, SIGGRAPH 2015
    PublisherAssociation for Computing Machinery, Inc
    ISBN (Print)9781450336321
    DOIs
    Publication statusPublished - 2015 Jul 31
    EventInternational Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2015 - Los Angeles, United States
    Duration: 2015 Aug 92015 Aug 13

    Other

    OtherInternational Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2015
    CountryUnited States
    CityLos Angeles
    Period15/8/915/8/13

    Fingerprint

    Color
    Textures
    Painting
    Paint
    Costs

    ASJC Scopus subject areas

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

    Cite this

    Yamaguchi, S., Furusawa, C., Kato, T., Fukusato, T., & Morishima, S. (2015). BG maker: Example-based anime background image creation from a photograph. In ACM SIGGRAPH 2015 Posters, SIGGRAPH 2015 [a45] Association for Computing Machinery, Inc. https://doi.org/10.1145/2787626.2787646

    BG maker : Example-based anime background image creation from a photograph. / Yamaguchi, Shugo; Furusawa, Chie; Kato, Takuya; Fukusato, Tsukasa; Morishima, Shigeo.

    ACM SIGGRAPH 2015 Posters, SIGGRAPH 2015. Association for Computing Machinery, Inc, 2015. a45.

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

    Yamaguchi, S, Furusawa, C, Kato, T, Fukusato, T & Morishima, S 2015, BG maker: Example-based anime background image creation from a photograph. in ACM SIGGRAPH 2015 Posters, SIGGRAPH 2015., a45, Association for Computing Machinery, Inc, International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2015, Los Angeles, United States, 15/8/9. https://doi.org/10.1145/2787626.2787646
    Yamaguchi S, Furusawa C, Kato T, Fukusato T, Morishima S. BG maker: Example-based anime background image creation from a photograph. In ACM SIGGRAPH 2015 Posters, SIGGRAPH 2015. Association for Computing Machinery, Inc. 2015. a45 https://doi.org/10.1145/2787626.2787646
    Yamaguchi, Shugo ; Furusawa, Chie ; Kato, Takuya ; Fukusato, Tsukasa ; Morishima, Shigeo. / BG maker : Example-based anime background image creation from a photograph. ACM SIGGRAPH 2015 Posters, SIGGRAPH 2015. Association for Computing Machinery, Inc, 2015.
    @inproceedings{366b3dd95b1840aebcfade4585e75479,
    title = "BG maker: Example-based anime background image creation from a photograph",
    abstract = "Anime designers often paint actual sceneries to serve as background images based on photographs to complement characters. As paint- ing background scenery is time consuming and cost ineffective, there is a high demand for techniques that can convert photographs into anime styled graphics. Previous approaches for this purpose, such as Image Quilting [Efros and Freeman 2001] transferred a source texture onto a target photograph. These methods synthesized corresponding source patches with the target elements in a photo- graph, and correspondence was achieved through nearest-neighbor search such as PatchMatch [Barnes et al. 2009]. However, the near- est-neighbor patch is not always the most suitable patch for anime transfer because photographs and anime background images differ in color and texture. For example, real-world color need to be con- verted into specific colors for anime; further, the type of brushwork required to realize an anime effect, is different for different photo- graph elements (e.g. sky, mountain, grass). Thus, to get the most suitable patch, we propose a method, wherein we establish global region correspondence before local patch match. In our proposed method, BGMaker, (1) we divide the real and anime images into re- gions; (2) then, we automatically acquire correspondence between each region on the basis of color and texture features, and (3) search and synthesize the most suitable patch within the corresponding re- gion. Our primary contribution in this paper is a method for au- Tomatically acquiring correspondence between target regions and source regions of different color and texture, which allows us to generate an anime background image while preserving the details of the source image.",
    author = "Shugo Yamaguchi and Chie Furusawa and Takuya Kato and Tsukasa Fukusato and Shigeo Morishima",
    year = "2015",
    month = "7",
    day = "31",
    doi = "10.1145/2787626.2787646",
    language = "English",
    isbn = "9781450336321",
    booktitle = "ACM SIGGRAPH 2015 Posters, SIGGRAPH 2015",
    publisher = "Association for Computing Machinery, Inc",

    }

    TY - GEN

    T1 - BG maker

    T2 - Example-based anime background image creation from a photograph

    AU - Yamaguchi, Shugo

    AU - Furusawa, Chie

    AU - Kato, Takuya

    AU - Fukusato, Tsukasa

    AU - Morishima, Shigeo

    PY - 2015/7/31

    Y1 - 2015/7/31

    N2 - Anime designers often paint actual sceneries to serve as background images based on photographs to complement characters. As paint- ing background scenery is time consuming and cost ineffective, there is a high demand for techniques that can convert photographs into anime styled graphics. Previous approaches for this purpose, such as Image Quilting [Efros and Freeman 2001] transferred a source texture onto a target photograph. These methods synthesized corresponding source patches with the target elements in a photo- graph, and correspondence was achieved through nearest-neighbor search such as PatchMatch [Barnes et al. 2009]. However, the near- est-neighbor patch is not always the most suitable patch for anime transfer because photographs and anime background images differ in color and texture. For example, real-world color need to be con- verted into specific colors for anime; further, the type of brushwork required to realize an anime effect, is different for different photo- graph elements (e.g. sky, mountain, grass). Thus, to get the most suitable patch, we propose a method, wherein we establish global region correspondence before local patch match. In our proposed method, BGMaker, (1) we divide the real and anime images into re- gions; (2) then, we automatically acquire correspondence between each region on the basis of color and texture features, and (3) search and synthesize the most suitable patch within the corresponding re- gion. Our primary contribution in this paper is a method for au- Tomatically acquiring correspondence between target regions and source regions of different color and texture, which allows us to generate an anime background image while preserving the details of the source image.

    AB - Anime designers often paint actual sceneries to serve as background images based on photographs to complement characters. As paint- ing background scenery is time consuming and cost ineffective, there is a high demand for techniques that can convert photographs into anime styled graphics. Previous approaches for this purpose, such as Image Quilting [Efros and Freeman 2001] transferred a source texture onto a target photograph. These methods synthesized corresponding source patches with the target elements in a photo- graph, and correspondence was achieved through nearest-neighbor search such as PatchMatch [Barnes et al. 2009]. However, the near- est-neighbor patch is not always the most suitable patch for anime transfer because photographs and anime background images differ in color and texture. For example, real-world color need to be con- verted into specific colors for anime; further, the type of brushwork required to realize an anime effect, is different for different photo- graph elements (e.g. sky, mountain, grass). Thus, to get the most suitable patch, we propose a method, wherein we establish global region correspondence before local patch match. In our proposed method, BGMaker, (1) we divide the real and anime images into re- gions; (2) then, we automatically acquire correspondence between each region on the basis of color and texture features, and (3) search and synthesize the most suitable patch within the corresponding re- gion. Our primary contribution in this paper is a method for au- Tomatically acquiring correspondence between target regions and source regions of different color and texture, which allows us to generate an anime background image while preserving the details of the source image.

    UR - http://www.scopus.com/inward/record.url?scp=84959368886&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84959368886&partnerID=8YFLogxK

    U2 - 10.1145/2787626.2787646

    DO - 10.1145/2787626.2787646

    M3 - Conference contribution

    AN - SCOPUS:84959368886

    SN - 9781450336321

    BT - ACM SIGGRAPH 2015 Posters, SIGGRAPH 2015

    PB - Association for Computing Machinery, Inc

    ER -