Presentation 2021-02-18
Design Creation with GAN using features that reflect Shape and Material
Shun Matsumura, Kiyoharu Aizawa, Atsushi Honda, Seiji Kurokoshi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When designers create a new design, they often refer to the existing design of shapes and materials to create a new design. The purpose of this study is to support such design creation. For this purpose, image data with label information of shape and material is necessary. However, images obtained by retrieval of web pages do not have such labels, so it is not possible to generate images using only the retrieved images. In this study, we define classes of Shape and Material attributes using Self-supervised methods and train each classifier. In synthesis, we aim to synthesize designs with different conditions by training Conditional GAN based on the estimation results of the Shape and Material estimators.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) GAN / Design Creation / Self-supervised learning
Paper # ITS2020-34,IE2020-48
Date of Issue 2021-02-11 (ITS, IE)

Conference Information
Committee IE / ITS / ITE-MMS / ITE-ME / ITE-AIT
Conference Date 2021/2/18(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Image Processing, etc.
Chair Hideaki Kimata(NTT) / Tomotaka Wada(Kansai Univ.) / Kenji Machida(NHK) / Hiroyuki Arai(Nippon Inst. of Tech.) / Nobuhiko Mukai(Tokyo City Univ.)
Vice Chair Kazuya Kodama(NII) / Keita Takahashi(Nagoya Univ.) / Yusuke Takatori(Kanagawa Inst. of Tech.) / Hiroyuki Hatano(Mie Univ.) / / Shogo Muramatsu(Niigata Univ.) / Hisaki Nate(Tokyo Polytechnic Univ.)
Secretary Kazuya Kodama(KDDI Research) / Keita Takahashi(Nagoya Inst. of Tech.) / Yusuke Takatori(Univ. of Tokyo) / Hiroyuki Hatano(Akita Prefectural Univ.) / (Fukuoka Univ.) / Shogo Muramatsu(NHK) / Hisaki Nate(Hokkaido Univ.)
Assistant Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Msataka Imao(Mitsubishi Electric) / Yanlei Gu(Ritsumeikan Univ.) / Kenshi Saho(Toyama Prefectural Univ.)

Paper Information
Registration To Technical Committee on Image Engineering / Technical Committee on Intelligent Transport Systems Technology / Technical Group on Multi-media Storage / Technical Group on Media Engineering / Technical Group on Artistic Image Technology
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Design Creation with GAN using features that reflect Shape and Material
Sub Title (in English)
Keyword(1) GAN
Keyword(2) Design Creation
Keyword(3) Self-supervised learning
1st Author's Name Shun Matsumura
1st Author's Affiliation The University of Tokyo(UTokyo)
2nd Author's Name Kiyoharu Aizawa
2nd Author's Affiliation The University of Tokyo(UTokyo)
3rd Author's Name Atsushi Honda
3rd Author's Affiliation DIGISEARCH AND ADVERTISING, INC .(DIGISEARCH)
4th Author's Name Seiji Kurokoshi
4th Author's Affiliation DIGISEARCH AND ADVERTISING, INC .(DIGISEARCH)
Date 2021-02-18
Paper # ITS2020-34,IE2020-48
Volume (vol) vol.120
Number (no) ITS-363,IE-364
Page pp.pp.43-48(ITS), pp.43-48(IE),
#Pages 6
Date of Issue 2021-02-11 (ITS, IE)