Abstract
Few-shot font generation (FFG) aims to preserve the underlying global structure of the original character while generating target fonts by referring to a few samples. It has been applied to font library creation, a personalized signature, and other scenarios. Existing FFG methods explicitly disentangle content and style of reference glyphs universally or component-wisely. However, they ignore the difference between glyphs in different styles and the similarity of glyphs in the same style, which results in artifacts such as local distortions and style inconsistency. To address this issue, we propose a novel font generation approach by learning the Difference between different styles and the Similarity of the same style (DS-Font). We introduce contrastive learning to consider the positive and negative relationship between styles. Specifically, we propose a multi-layer style projector for style encoding and realize a distinctive style representation via our proposed Cluster-level Contrastive Style (CCS) loss. In addition, we design a multi-task patch discriminator, which comprehensively considers different areas of the image and ensures that each style can be distinguished independently. We conduct qualitative and quantitative evaluations comprehensively to demonstrate that our approach achieves significantly better results than state-of-the-art methods.
Abstract (translated)
有限次数字体生成(FFG)旨在通过引用少量样本生成目标字体,同时保留原始字符的全局结构。它已被应用于字体库创建、个性化签名和其他场景。现有的FFG方法明确分离参考字体的内容和风格,普遍或按组件分解。然而,它们忽略了不同风格之间的差异和相同风格的相似性,导致失真局部和风格不一致等 artifacts。为了解决这个问题,我们提出了一种新字体生成方法,通过学习不同风格之间的差异和相同风格的相似性(DS-Font)。我们引入了比较学习,考虑风格之间的积极和消极关系。具体来说,我们提出了一种多层风格投影,用于风格编码,并通过我们提出的 Cluster-level Contrastive Style (CCS) 损失实现独特的风格表示。此外,我们设计了一个多任务 patch discriminator,全面考虑图像的不同区域,确保每种风格可以独立区分。我们进行全面定性和定量评估,证明我们的方法比现有方法实现更好的结果。
URL
https://arxiv.org/abs/2301.10008