| Presentation | 2022-02-21 Illustration author style translation using SailormoonRedraw data Keita Awane, Daichi Horita, Hikaru Ikuta, Yusuke Matsui, Naohiro Yanase, Kiyoharu Aizawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The author characteristics of illustrations can be divided into two elements: "what to draw" and "how to draw". The latter is called "author style" and is an important factor in illustration. We propose a deep learning-based method that auto- matically translates one’s illustration into another author’s style. Existing unsupervised image translation methods only replace textures, so they cannot achieve author style translation that requires structural transformation while maintaining the character. To solve this problem, we created a novel illustration dataset, SailormoonDataset, which consists of SailormoonRedraw data. We then propose a supervised learning method using the content consistency of the SailormoonDataset. As a first step, we translated the face illustration of Sailormoon. Through experiments, we confirmed that the proposed method achieves the style translation not only by textural but also by structural transformation while maintaining the identity of Sailormoon. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep Learning / Image Generation / Image Translation / Support System for Illustration Production |
| Paper # | ITS2021-26,IE2021-35 |
| Date of Issue | 2022-02-14 (ITS, IE) |
| Conference Information | |
| Committee | IE / ITS / ITE-AIT / ITE-ME / ITE-MMS |
|---|---|
| Conference Date | 2022/2/21(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Image Processing, etc. |
| Chair | Kazuya Kodama(NII) / Masahiro Fujii(Utsunomiya Univ.) / Hisaki Nate(Tokyo Polytechnic Univ.) / Hiroyuki Arai(Nippon Inst. of Tech.) / Kenji Machida(NHK) |
| Vice Chair | Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(Univ. of Tokyo) / Kohei Ohno(Meiji Univ.) / Naohisa Hashimoto(AIST) / / Shogo Muramatsu(Niigata Univ.) |
| Secretary | Hiroyuki Bandoh(KDDI Research) / Toshihiko Yamazaki(Nagoya Inst. of Tech.) / Kohei Ohno(Akita Prefectural Univ.) / Naohisa Hashimoto(NIT, Tsuruoka College) / / Shogo Muramatsu(NHK) / (Hokkaido Univ.) |
| Assistant | Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Msataka Imao(Mitsubishi Electric) / Kenshi Saho(Toyama Prefectural Univ.) / Keiji Jimi(Gunma Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Image Engineering / Technical Committee on Intelligent Transport Systems Technology / Technical Group on Artistic Image Technology / Technical Group on Media Engineering / Technical Group on Multi-media Storage |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Illustration author style translation using SailormoonRedraw data |
| Sub Title (in English) | |
| Keyword(1) | Deep Learning |
| Keyword(2) | Image Generation |
| Keyword(3) | Image Translation |
| Keyword(4) | Support System for Illustration Production |
| 1st Author's Name | Keita Awane |
| 1st Author's Affiliation | The University of Tokyo(UTokyo) |
| 2nd Author's Name | Daichi Horita |
| 2nd Author's Affiliation | The University of Tokyo(UTokyo) |
| 3rd Author's Name | Hikaru Ikuta |
| 3rd Author's Affiliation | The University of Tokyo(UTokyo) |
| 4th Author's Name | Yusuke Matsui |
| 4th Author's Affiliation | The University of Tokyo(UTokyo) |
| 5th Author's Name | Naohiro Yanase |
| 5th Author's Affiliation | BOOK WALKER Co.,Ltd.(BOOK WALKER) |
| 6th Author's Name | Kiyoharu Aizawa |
| 6th Author's Affiliation | The University of Tokyo(UTokyo) |
| Date | 2022-02-21 |
| Paper # | ITS2021-26,IE2021-35 |
| Volume (vol) | vol.121 |
| Number (no) | ITS-373,IE-374 |
| Page | pp.pp.7-12(ITS), pp.7-12(IE), |
| #Pages | 6 |
| Date of Issue | 2022-02-14 (ITS, IE) |