Chinese Typography Transfer
Abstract
In this paper, we propose a new network architecture for Chinese typography transformation based on deep learning. The architecture consists of two sub-networks: (1)a fully convolutional network(FCN) aiming at transferring specified typography style to another in condition of preserving structure information; (2)an adversarial network aiming at generating more realistic strokes in some details. Unlike models proposed before 2012 relying on the complex segmentation of Chinese components or strokes, our model treats every Chinese character as an inseparable image, so pre-processing or post-preprocessing are abandoned. Besides, our model adopts end-to-end training without pre-trained used in other deep models. The experiments demonstrates that our model can synthesize realistic-looking target typography from any source typography both on printed style and handwriting style.
Cite
@article{arxiv.1707.04904,
title = {Chinese Typography Transfer},
author = {Jie Chang and Yujun Gu},
journal= {arXiv preprint arXiv:1707.04904},
year = {2017}
}
Comments
There is an error in Figure 5.(b) where the figure caption is "evaluation mse" instead of "Loss curve". It can lead to the misunderstanding of my performance under different configuration. So I request to withdraw