A Learned Representation for Scalable Vector Graphics

Raphael Gontijo Lopes, David Ha, Douglas Eck, Jonathon Shlens

Keywords: Representation Learning, Image Synthesis, Computer Vision, Applications, Deep Learning, Scalable Vector Graphics, Font Generation

TL;DR: We attempt to model the drawing process of fonts by building sequential generative models of vector graphics (SVGs), a highly structured representation of font characters.

Abstract: Dramatic advances in generative models have resulted in near photographic quality for artificially rendered faces, animals and other objects in the natural world.In spite of such advances, a higher level understanding of vision and imagery does not arise from exhaustively modeling an object, but instead identifying higher-level attributes that best summarize the aspects of an object. In this work we attempt to model the drawing process of fonts by building sequential generative models of vector graphics. This model has the benefit of providing a scale-invariant representation for imagery whose latent representation may be systematically manipulated and exploited to perform style propagation. We demonstrate these results on a large dataset of fonts and highlight how such a model captures the statistical dependencies and richness of this dataset. We envision that our model can find use as a tool for designers to facilitate font design.

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:1904.02632/code)