Fonts are ubiquitous across documents and come in a variety of styles. They are either represented in a native vector format or rasterized to produce fixed resolution images. In the first case, the non-standard representation prevents benefiting from latest network architectures for neural representations; while, in the latter case, the rasterized representation, when encoded via networks, results in loss of data fidelity, as font-specific discontinuities like edges and corners are difficult to represent using neural networks. Based on the observation that complex fonts can be represented by a superposition of a set of simpler occupancy functions, we introduce \textit{multi-implicits} to represent fonts as a permutation-invariant set of learned implict functions, without losing features (e.g., edges and corners). However, while multi-implicits locally preserve font features, obtaining supervision in the form of ground truth multi-channel signals is a problem in itself. Instead, we propose how to train such a representation with only local supervision, while the proposed neural architecture directly finds globally consistent multi-implicits for font families. We extensively evaluate the proposed representation for various tasks including reconstruction, interpolation, and synthesis to demonstrate clear advantages with existing alternatives. Additionally, the representation naturally enables glyph completion, wherein a single characteristic font is used to synthesize a whole font family in the target style.
翻译:字体在文档中是无处不在的, 并且有各种各样的风格。 它们或者以本地矢量格式表示, 或者以光化形式表示, 以生成固定分辨率图像。 在第一种情况下, 非标准表示无法从神经显示的最新网络结构中受益; 在后一种情况下, 光化表示, 当通过网络编码时, 导致数据忠诚度的丧失, 因为像边缘和角这样的字体特定不一致性很难使用神经网络来代表 。 根据这样的观察, 复杂的字体可以通过一组更简单的占用功能的叠加来代表。 我们引入了\ textitle{ 多重implicits} 来代表字体, 作为学习的不透性功能的变异性组合; 在后一种情况下, 当通过网络编码( 如边缘和角落) 编码时, 光化的表达方式, 导致数据忠诚。 然而, 多重隐含本地保存字体特征, 以地面真相多频道信号的形式进行监管本身就是个问题本身。 相反, 我们提议如何在仅由本地监督的情况下, 来培训这种代表, 而拟议的神经结构则直接找到全球一致的风格风格风格风格, 能够让各种的字体的字体代表方式展示。