English

Learning to Generate Poetic Chinese Landscape Painting with Calligraphy

Computer Vision and Pattern Recognition 2023-05-09 v1

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.

Keywords

Cite

@article{arxiv.2305.04719,
  title  = {Learning to Generate Poetic Chinese Landscape Painting with Calligraphy},
  author = {Shaozu Yuan and Aijun Dai and Zhiling Yan and Ruixue Liu and Meng Chen and Baoyang Chen and Zhijie Qiu and Xiaodong He},
  journal= {arXiv preprint arXiv:2305.04719},
  year   = {2023}
}

Comments

Accepted by IJCAI 2022