| Presentation | 2018-03-18 A Style Transfer Method using Variational Autoencoder Hidemoto Nakada, Hideki Asoh, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Image Style Transfer is a technique to render arbitrary image content with arbitrary image 'style'. Most existing image transfer method requires certain amount of time to gradually modify the image itself or to train a transfer network for each style image. We propose a Variational Autoencoder based method which uses style latent variable which is separated from the content latent variable. The proposed network does not require training for each style image and can generate a transfer image with arbitrary content image and arbitrary style image immediately. We introduced separation term between the two kinds of latent variables to the training loss. We confirmed that the proposed method can produce style transferred image with relatively good quality. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Style Transfer / Variational Autoencoder / Deep learning |
| Paper # | BioX2017-56,PRMU2017-192 |
| Date of Issue | 2018-03-11 (BioX, PRMU) |
| Conference Information | |
| Committee | PRMU / BioX |
|---|---|
| Conference Date | 2018/3/18(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) / Kazuhiko Sumi(AGU) |
| Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Hiroshi Takano(Toyama Pref. Univ.) / Hitoshi Imaoka(NEC) |
| Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Hiroshi Takano(Shizuoka Univ.) / Hitoshi Imaoka(Fujitsu Labs.) |
| Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Masatsugu Ichino(Univ. of Electro-Comm.) / Naoyuki Takada(Secom) / Norihiro Okui(KDDI Research) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Biometrics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Style Transfer Method using Variational Autoencoder |
| Sub Title (in English) | |
| Keyword(1) | Style Transfer |
| Keyword(2) | Variational Autoencoder |
| Keyword(3) | Deep learning |
| 1st Author's Name | Hidemoto Nakada |
| 1st Author's Affiliation | National Institute of Advanced Industrial Science and Technology(AIST) |
| 2nd Author's Name | Hideki Asoh |
| 2nd Author's Affiliation | National Institute of Advanced Industrial Science and Technology(AIST) |
| Date | 2018-03-18 |
| Paper # | BioX2017-56,PRMU2017-192 |
| Volume (vol) | vol.117 |
| Number (no) | BioX-513,PRMU-514 |
| Page | pp.pp.121-126(BioX), pp.121-126(PRMU), |
| #Pages | 6 |
| Date of Issue | 2018-03-11 (BioX, PRMU) |