论文标题
attribute2font：创建您想要的字体
Attribute2Font: Creating Fonts You Want From Attributes
论文作者
论文摘要
现在，字体设计仍被视为专业设计师的独家特权，其创造力不受现有软件系统的创造力。 Nevertheless, we also notice that most commercial font products are in fact manually designed by following specific requirements on some attributes of glyphs, such as italic, serif, cursive, width, angularity, etc. Inspired by this fact, we propose a novel model, Attribute2Font, to automatically create fonts by synthesizing visually-pleasing glyph images according to user-specified attributes and their corresponding values.据我们所知，我们的模型是文献中的第一个模型，它能够根据指定的字体属性的给定值来生成新字体样式中的字形图像，而不是检索现有字体。具体而言，训练属性2font可以在以其属性值为条件的任何两个字体之间执行字体样式传输。训练后，我们的模型可以根据一组任意的字体属性值生成字形图像。此外，一个名为“属性注意”模块的新型单元旨在使那些生成的字形图像更好地体现出突出的字体属性。考虑到字体属性值的注释非常昂贵，还引入了半监督学习方案，以利用大量未标记的字体。实验结果表明，我们的模型在许多任务上取得了令人印象深刻的性能，例如在新字体样式中创建字形图像，编辑现有字体，不同字体之间的插值等。
Font design is now still considered as an exclusive privilege of professional designers, whose creativity is not possessed by existing software systems. Nevertheless, we also notice that most commercial font products are in fact manually designed by following specific requirements on some attributes of glyphs, such as italic, serif, cursive, width, angularity, etc. Inspired by this fact, we propose a novel model, Attribute2Font, to automatically create fonts by synthesizing visually-pleasing glyph images according to user-specified attributes and their corresponding values. To the best of our knowledge, our model is the first one in the literature which is capable of generating glyph images in new font styles, instead of retrieving existing fonts, according to given values of specified font attributes. Specifically, Attribute2Font is trained to perform font style transfer between any two fonts conditioned on their attribute values. After training, our model can generate glyph images in accordance with an arbitrary set of font attribute values. Furthermore, a novel unit named Attribute Attention Module is designed to make those generated glyph images better embody the prominent font attributes. Considering that the annotations of font attribute values are extremely expensive to obtain, a semi-supervised learning scheme is also introduced to exploit a large number of unlabeled fonts. Experimental results demonstrate that our model achieves impressive performance on many tasks, such as creating glyph images in new font styles, editing existing fonts, interpolation among different fonts, etc.
