Presentation | 2023-09-12 大規模条件付き画像生成モデルを用いたテキストによる出力制御可能なアイコン線画彩色 Koki Miyauchi, Ryohei Orihara, Yuichi Sei, Yasuyuki Tahara, Akihiko Ohsuga, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Icons are indispensable elements for websites and smartphone applications. For website developers, the creation of icons poses a formidable challenge. Specifically, it is difficult to color without deviating from the line art of the icon. It is also challenging to paint line drawings while maintaining a consistent style. In order to address this problem, we propose an innovative approach to icon generation that leverages Stable Diffusion, an expansive model for generating images, and enables textual control over the generated output. Specifically, we painted line drawings using a Stable Diffusion-based image generation model, Uni-ControlNet, which operates on multiple conditions to generate images. To facilitate the training of this model, we assembled a dataset comprising icons in the gradient style, along with their corresponding captions. We proposed a quantitative index to evaluate the similarity of gradients between reference images and colored line drawings. Our method was shown to be able to color icons with hollow structures, which was difficult with existing methods. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Automatic Colorization / Diffusion Model / Conditional Generation / Icon Design |
Paper # | AI2023-34 |
Date of Issue | 2023-09-05 (AI) |
Conference Information | |
Committee | AI |
---|---|
Conference Date | 2023/9/12(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Katsuhide Fujita(Tokyo Univ. of Agriculture and Technology) |
Vice Chair | Yuko Sakurai(agoya Inst. of Tech.) / Tadachika Ozono(Nagoya Inst. of Tech.) |
Secretary | Yuko Sakurai(Chuo Univ.) / Tadachika Ozono(Toho Univ.) |
Assistant |
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) | Automatic Colorization |
Keyword(2) | Diffusion Model |
Keyword(3) | Conditional Generation |
Keyword(4) | Icon Design |
1st Author's Name | Koki Miyauchi |
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 | 2023-09-12 |
Paper # | AI2023-34 |
Volume (vol) | vol.123 |
Number (no) | AI-190 |
Page | pp.pp.201-206(AI), |
#Pages | 6 |
Date of Issue | 2023-09-05 (AI) |