Generalized W-Net: Arbitrary-style Chinese Character Synthesization
This addresses the challenge of generating stylized Chinese characters for applications like font design, but it is incremental as it builds on existing W-shaped architectures.
The paper tackles the problem of synthesizing Chinese characters with consistent style using few stylized examples, and the result is a Generalized W-Net that can generate arbitrary style characters with limited examples, handling seen and unseen styles during training.
Synthesizing Chinese characters with consistent style using few stylized examples is challenging. Existing models struggle to generate arbitrary style characters with limited examples. In this paper, we propose the Generalized W-Net, a novel class of W-shaped architectures that addresses this. By incorporating Adaptive Instance Normalization and introducing multi-content, our approach can synthesize Chinese characters in any desired style, even with limited examples. It handles seen and unseen styles during training and can generate new character contents. Experimental results demonstrate the effectiveness of our approach.