Automatic Generation of Chinese Handwriting via Fonts Style Representation Learning
This work addresses font design efficiency for Chinese typography, but it appears incremental as it builds on existing methods with claimed simplifications.
The paper tackles the problem of generating Chinese handwriting fonts by proposing an end-to-end deep learning system that uses latent style embeddings for interpolation, enabling smooth style transitions and improving font design efficiency.
In this paper, we propose and end-to-end deep Chinese font generation system. This system can generate new style fonts by interpolation of latent style-related embeding variables that could achieve smooth transition between different style. Our method is simpler and more effective than other methods, which will help to improve the font design efficiency