CanvasVAE: Learning to Generate Vector Graphic Documents
This work addresses the need for generative models in creative applications, but it is incremental as it builds on existing VAE methods.
The authors tackled the problem of generating vector graphic documents by training variational auto-encoders on a new dataset of design templates, showing that CanvasVAE serves as a strong baseline for this task.
Vector graphic documents present visual elements in a resolution free, compact format and are often seen in creative applications. In this work, we attempt to learn a generative model of vector graphic documents. We define vector graphic documents by a multi-modal set of attributes associated to a canvas and a sequence of visual elements such as shapes, images, or texts, and train variational auto-encoders to learn the representation of the documents. We collect a new dataset of design templates from an online service that features complete document structure including occluded elements. In experiments, we show that our model, named CanvasVAE, constitutes a strong baseline for generative modeling of vector graphic documents.