VecFusion：使用擴散生成向量字型

VecFusion: Vector Font Generation with Diffusion

December 16, 2023

作者: Vikas Thamizharasan, Difan Liu, Shantanu Agarwal, Matthew Fisher, Michael Gharbi, Oliver Wang, Alec Jacobson, Evangelos Kalogerakis

cs.AI

摘要

我們提出了VecFusion，一種新的神經架構，可以生成具有不同拓撲結構和精確控制點位置的向量字體。我們的方法是一種級聯擴散模型，包括光柵擴散模型和向量擴散模型。光柵模型生成低分辨率的光柵字體，附帶輔助控制點信息，捕捉字體的全局風格和形狀，而向量模型則根據第一階段的低分辨率光柵字體合成向量字體。為了合成長且複雜的曲線，我們的向量擴散模型使用了變壓器架構和一種新穎的向量表示，使得能夠對多樣的向量幾何進行建模並精確預測控制點。我們的實驗表明，與以往用於向量圖形的生成模型相比，我們的新級聯向量擴散模型生成了質量更高、結構更複雜且風格更多樣的向量字體。

English

We present VecFusion, a new neural architecture that can generate vector fonts with varying topological structures and precise control point positions. Our approach is a cascaded diffusion model which consists of a raster diffusion model followed by a vector diffusion model. The raster model generates low-resolution, rasterized fonts with auxiliary control point information, capturing the global style and shape of the font, while the vector model synthesizes vector fonts conditioned on the low-resolution raster fonts from the first stage. To synthesize long and complex curves, our vector diffusion model uses a transformer architecture and a novel vector representation that enables the modeling of diverse vector geometry and the precise prediction of control points. Our experiments show that, in contrast to previous generative models for vector graphics, our new cascaded vector diffusion model generates higher quality vector fonts, with complex structures and diverse styles.