Region-based painting style transfer

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

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

    Abstract

    In this paper, we present a novel method for creating a painted im- Age from a photograph using an existing painting as a style source. The core idea is to identify the corresponding objects in the two images in order to select patches more appropriately. We automat- ically make a region correspondence between the painted source image and the target photograph by computing color and texture feature distances. Next, we conduct a patch-based synthesis that preserves the appropriate source and target features. Unlike previ- ous example-based approaches of painting style transfer, our results successfully reflect the features of the source images even if the in- put images have various colors and textures. Our method allows us to automatically render a new painted image preserving the features of the source image.

    Original languageEnglish
    Title of host publicationSIGGRAPH Asia 2015 Technical Briefs, SA 2015
    PublisherAssociation for Computing Machinery, Inc
    ISBN (Print)9781450339308
    DOIs
    Publication statusPublished - 2015 Nov 2
    EventSIGGRAPH Asia, SA 2015 - Kobe, Japan
    Duration: 2015 Nov 22015 Nov 6

    Other

    OtherSIGGRAPH Asia, SA 2015
    CountryJapan
    CityKobe
    Period15/11/215/11/6

    Keywords

    • NPR
    • Style transfer
    • Texture synthesis

    ASJC Scopus subject areas

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

    Fingerprint Dive into the research topics of 'Region-based painting style transfer'. Together they form a unique fingerprint.

  • Cite this

    Yamaguchi, S., Kato, T., Fukusato, T., Furusawa, C., & Morishima, S. (2015). Region-based painting style transfer. In SIGGRAPH Asia 2015 Technical Briefs, SA 2015 [2820917] Association for Computing Machinery, Inc. https://doi.org/10.1145/2820903.2820917