Learning to Generate Poetic Chinese Landscape Painting with Calligraphy

Abstract

In this paper, we present a novel system (denoted as Polaca) to generate poetic Chinese landscape painting with calligraphy. Unlike previous single image-to-image painting generation, Polaca takes the classic poetry as input and outputs the artistic landscape painting image with the corresponding calligraphy. It is equipped with three different modules to complete the whole piece of landscape painting artwork: the first one is a text-to-image module to generate landscape painting image, the second one is an image-to-image module to generate stylistic calligraphy image, and the third one is an image fusion module to fuse the two images into a whole piece of aesthetic artwork.

Cite

Text

Yuan et al. "Learning to Generate Poetic Chinese Landscape Painting with Calligraphy." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/696

Markdown

[Yuan et al. "Learning to Generate Poetic Chinese Landscape Painting with Calligraphy." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/yuan2022ijcai-learning/) doi:10.24963/IJCAI.2022/696

BibTeX

@inproceedings{yuan2022ijcai-learning,
  title     = {{Learning to Generate Poetic Chinese Landscape Painting with Calligraphy}},
  author    = {Yuan, Shaozu and Dai, Aijun and Yan, Zhiling and Liu, Ruixue and Chen, Meng and Chen, Baoyang and Qiu, Zhijie and He, Xiaodong},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {5019-5022},
  doi       = {10.24963/IJCAI.2022/696},
  url       = {https://mlanthology.org/ijcai/2022/yuan2022ijcai-learning/}
}