Chinese calligraphy can be viewed as a unique form of visual art. Recent advancements in computer vision hold significant potential for the future development of generative models in the realm of Chinese calligraphy. Nevertheless, methods of Chinese calligraphy inpainting, which can be effectively used in the art and education fields, remain relatively unexplored. In this paper, we introduce a new model that harnesses recent advancements in both Chinese calligraphy generation and image inpainting. We demonstrate that our proposed model CalliPaint can produce convincing Chinese calligraphy.
@article{arxiv.2312.01536,
title = {CalliPaint: Chinese Calligraphy Inpainting with Diffusion Model},
author = {Qisheng Liao and Zhinuo Wang and Muhammad Abdul-Mageed and Gus Xia},
journal= {arXiv preprint arXiv:2312.01536},
year = {2023}
}
Comments
Accepted as a Machine Learning for Creativity and Design(ML4CD) workshop paper at NeruaIPS 2023. https://neurips.cc/virtual/2023/workshop/66545#wse-detail-75063