CanvasVAE: Learning to Generate Vector Graphic Documents

Abstract

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.

Cite

Text

Yamaguchi. "CanvasVAE: Learning to Generate Vector Graphic Documents." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.00543

Markdown

[Yamaguchi. "CanvasVAE: Learning to Generate Vector Graphic Documents." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/yamaguchi2021iccv-canvasvae/) doi:10.1109/ICCV48922.2021.00543

BibTeX

@inproceedings{yamaguchi2021iccv-canvasvae,
  title     = {{CanvasVAE: Learning to Generate Vector Graphic Documents}},
  author    = {Yamaguchi, Kota},
  booktitle = {International Conference on Computer Vision},
  year      = {2021},
  pages     = {5481-5489},
  doi       = {10.1109/ICCV48922.2021.00543},
  url       = {https://mlanthology.org/iccv/2021/yamaguchi2021iccv-canvasvae/}
}