Home > Research > Publications & Outputs > Improving style similarity metrics of 3D shapes

Electronic data

  • StyleSimilarity_GI

    Rights statement: © Owner/Author, 2016. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of Graphics Interface 2016 http://dx.doi.org/10.20380/GI2016.22

    Accepted author manuscript, 12.2 MB, PDF document

Links

Text available via DOI:

View graph of relations

Improving style similarity metrics of 3D shapes

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Improving style similarity metrics of 3D shapes. / Dev, Kapil; Kim, Kwang In; Villar, Nicolas et al.
Proceedings of Graphics Interface 2016: Victoria, British Columbia, Canada: 1-3 June 2016. Canadian Human-Computer Communications Society / Société canadienne du dialogue humain-machine., 2016.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Dev, K, Kim, KI, Villar, N & Lau, M 2016, Improving style similarity metrics of 3D shapes. in Proceedings of Graphics Interface 2016: Victoria, British Columbia, Canada: 1-3 June 2016. Canadian Human-Computer Communications Society / Société canadienne du dialogue humain-machine. https://doi.org/10.20380/GI2016.22

APA

Dev, K., Kim, K. I., Villar, N., & Lau, M. (2016). Improving style similarity metrics of 3D shapes. In Proceedings of Graphics Interface 2016: Victoria, British Columbia, Canada: 1-3 June 2016 Canadian Human-Computer Communications Society / Société canadienne du dialogue humain-machine.. https://doi.org/10.20380/GI2016.22

Vancouver

Dev K, Kim KI, Villar N, Lau M. Improving style similarity metrics of 3D shapes. In Proceedings of Graphics Interface 2016: Victoria, British Columbia, Canada: 1-3 June 2016. Canadian Human-Computer Communications Society / Société canadienne du dialogue humain-machine. 2016 doi: 10.20380/GI2016.22

Author

Dev, Kapil ; Kim, Kwang In ; Villar, Nicolas et al. / Improving style similarity metrics of 3D shapes. Proceedings of Graphics Interface 2016: Victoria, British Columbia, Canada: 1-3 June 2016. Canadian Human-Computer Communications Society / Société canadienne du dialogue humain-machine., 2016.

Bibtex

@inproceedings{fef62d09738140de955b0319180bec28,
title = "Improving style similarity metrics of 3D shapes",
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 similaritymetrics 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 theeffect 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.",
author = "Kapil Dev and Kim, {Kwang In} and Nicolas Villar and Manfred Lau",
note = "{\textcopyright} Owner/Author, 2016. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of Graphics Interface 2016 http://dx.doi.org/10.20380/GI2016.22 ",
year = "2016",
month = jun,
day = "1",
doi = "10.20380/GI2016.22",
language = "English",
isbn = "9780994786814",
booktitle = "Proceedings of Graphics Interface 2016",
publisher = "Canadian Human-Computer Communications Society / Soci{\'e}t{\'e} canadienne du dialogue humain-machine.",

}

RIS

TY - GEN

T1 - Improving style similarity metrics of 3D shapes

AU - Dev, Kapil

AU - Kim, Kwang In

AU - Villar, Nicolas

AU - Lau, Manfred

N1 - © Owner/Author, 2016. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of Graphics Interface 2016 http://dx.doi.org/10.20380/GI2016.22

PY - 2016/6/1

Y1 - 2016/6/1

N2 - 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 similaritymetrics 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 theeffect 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.

AB - 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 similaritymetrics 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 theeffect 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.

U2 - 10.20380/GI2016.22

DO - 10.20380/GI2016.22

M3 - Conference contribution/Paper

SN - 9780994786814

BT - Proceedings of Graphics Interface 2016

PB - Canadian Human-Computer Communications Society / Société canadienne du dialogue humain-machine.

ER -