Local Style Awareness of Font Images
This work addresses the challenge of generating accurate fonts with specific local styles, such as serifs, for applications in typography and design, though it is incremental as it builds on existing font generation models.
The paper tackles the problem of font generation by focusing on local style parts like serifs, proposing an attention mechanism to identify important local features and a reconstruction loss that weights these parts more heavily, which improves the quality of generated character images across several few-shot font generation models.
When we compare fonts, we often pay attention to styles of local parts, such as serifs and curvatures. This paper proposes an attention mechanism to find important local parts. The local parts with larger attention are then considered important. The proposed mechanism can be trained in a quasi-self-supervised manner that requires no manual annotation other than knowing that a set of character images is from the same font, such as Helvetica. After confirming that the trained attention mechanism can find style-relevant local parts, we utilize the resulting attention for local style-aware font generation. Specifically, we design a new reconstruction loss function to put more weight on the local parts with larger attention for generating character images with more accurate style realization. This loss function has the merit of applicability to various font generation models. Our experimental results show that the proposed loss function improves the quality of generated character images by several few-shot font generation models.