Proceedings: GI 2016

Improving Style Similarity Metrics of 3D Shapes

Kapil Dev (Lancaster University), Kwang Kim (Lancaster University), Nicolas Villar (Microsoft Research Cambridge), Manfred Lau (Lancaster University)

Proceedings of Graphics Interface 2016: Victoria, British Columbia, Canada, 1-3 June 2016, 175-182

DOI 10.20380/GI2016.22

  • Bibtex

    @inproceedings{Dev:2016:10.20380/GI2016.22,
    author = {Dev, Kapil and Kim, Kwang and Villar, Nicolas and Lau, Manfred},
    title = {Improving Style Similarity Metrics of 3D Shapes},
    booktitle = {Proceedings of Graphics Interface 2016},
    series = {GI 2016},
    year = {2016},
    issn = {0713-5424},
    isbn = {978-0-9947868-1-4},
    location = {Victoria, British Columbia, Canada},
    pages = {175--182},
    numpages = {8},
    doi = {10.20380/GI2016.22},
    publisher = {Canadian Human-Computer Communications Society / Soci{\'e}t{\'e} canadienne du dialogue humain-machine},
    }

Abstract

The idea of style similarity metrics has been recently developed for various media types such as 2D clip art and 3D shapes. We explore this style metric problem and improve existing style similarity metrics of 3D shapes in four novel ways. First, we consider the color and texture of 3D shapes which are important properties that have not been previously considered. Second, we explore the effect of clustering a dataset of 3D models by comparing between style metrics for individual object types and style metrics that combine clusters of object types. Third, we explore the idea of userguided learning for this problem. Fourth, we introduce an iterative approach that can learn a metric from a general set of 3D models. We demonstrate these contributions with various classes of 3D shapes and with applications such as style-based similarity search and scene composition.