Abstract
This work introduces Self-Stylized Neural Painter (SSNP) creating stylized artworks in a stroke-by-stroke manner. SSNP consists of digit artist, canvas, style-stroke generator (SSG). By using SSG to generate style strokes, SSNP creates different styles paintings based on the given images. We design SSG as a three-player game based on a generative adversarial network to produce pure-color strokes that are crucial for mimicking the physical strokes. Furthermore, the digital artist adjusts parameters of strokes (shape, size, transparency, and color) to reconstruct as much detailed content of the reference image as possible to improve the fidelity.
| Original language | English |
|---|---|
| Pages | 1-2 |
| DOIs | |
| Publication status | Published - 14 Dec 2021 |
| Event | SIGGRAPH Asia 2021 Posters - Computer Graphics and Interactive Techniques Conference - Asia, SA 2021 - Tokyo, Japan Duration: 14 Dec 2021 → 17 Dec 2021 |
Conference
| Conference | SIGGRAPH Asia 2021 Posters - Computer Graphics and Interactive Techniques Conference - Asia, SA 2021 |
|---|---|
| Country/Territory | Japan |
| City | Tokyo |
| Period | 14/12/21 → 17/12/21 |
Bibliographical note
Publisher Copyright:© 2021 Owner/Author.
Funding
The work was supported by Macau Science and Technology Development Fund under Key R &D Projects (0025/2019/AKP), and by The Hong Kong Polytechnic University (P0030419).