| Presentation | 2022-07-04 スタイルとコンテントを分離した背景画像の編集の検討 Syuusuke Ishihata, Ryohei Orihara, Yuichi Sei, Yasuyuki Tahara, Akihiko Ohsuga, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, research has been conducted to apply StyleGAN to the task of editing images according to the content of natural language input, as in StyleCLIP, where latent variables are modified so that images can be generated according to the content of the text. This method can also be applied to editing background images, but it is difficult to freely edit backgrounds using only text, because background images are more diverse than face images and the specification of content is ambiguous using only text. In addition to StyleCLIP, this study used HyperStyle, an encoder-based GAN Inversion method, to separate the style and content of background images. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | StyleCLIP / natural language / Image Editing / Bacground / GAN Inversion |
| Paper # | AI2022-1 |
| Date of Issue | 2022-06-27 (AI) |
| Conference Information | |
| Committee | AI |
|---|---|
| Conference Date | 2022/7/4(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Yuichi Sei(Univ. of Electro-Comm.) |
| Vice Chair | Yuko Sakurai(AIST) / Tadachika Ozono(Nagoya Inst. of Tech.) |
| Secretary | Yuko Sakurai(Tokyo Univ. of Agriculture and Technology) / Tadachika Ozono(Toho Univ.) |
| Assistant | Kazutaka Matsuzaki(Chuo Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Artificial Intelligence and Knowledge-Based Processing |
|---|---|
| Language | JPN-ONLY |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | |
| Sub Title (in English) | |
| Keyword(1) | StyleCLIP |
| Keyword(2) | natural language |
| Keyword(3) | Image Editing |
| Keyword(4) | Bacground |
| Keyword(5) | GAN Inversion |
| 1st Author's Name | Syuusuke Ishihata |
| 1st Author's Affiliation | The University of Electro-Communications(UEC) |
| 2nd Author's Name | Ryohei Orihara |
| 2nd Author's Affiliation | The University of Electro-Communications(UEC) |
| 3rd Author's Name | Yuichi Sei |
| 3rd Author's Affiliation | The University of Electro-Communications(UEC) |
| 4th Author's Name | Yasuyuki Tahara |
| 4th Author's Affiliation | The University of Electro-Communications(UEC) |
| 5th Author's Name | Akihiko Ohsuga |
| 5th Author's Affiliation | The University of Electro-Communications(UEC) |
| Date | 2022-07-04 |
| Paper # | AI2022-1 |
| Volume (vol) | vol.122 |
| Number (no) | AI-94 |
| Page | pp.pp.1-6(AI), |
| #Pages | 6 |
| Date of Issue | 2022-06-27 (AI) |