Modelling complex vector drawings with stroke-clouds

Alexander Ashcroft, Ayan Das, Yulia Gryaditskaya, Zhiyu Qu, Yi-Zhe Song

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Generative Model, Representation Learning, Sets, Vector Graphics

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract:

Vector drawings are innately interactive as they preserve creational cues. Despite
this desirable property they remain relatively under explored due to the difficulties
in modeling complex vector drawings. This is in part due to the primarily _sequential and auto-regressive nature_ of existing approaches failing to scale beyond simple
drawings. In this paper, we define generative models over _highly complex_ vector
drawings by first representing them as “stroke-clouds” – _sets_ of arbitrary cardinality comprised of semantically meaningful strokes. The dimensionality of the
strokes is a design choice that allows the model to adapt to a range of complexities.
We learn to encode these _set of strokes_ into compact latent codes by a probabilistic
reconstruction procedure backed by _De-Finetti’s Theorem of Exchangability_. The
parametric generative model is then defined over the latent vectors of the encoded
stroke-clouds. The resulting “Latent stroke-cloud generator (LSG)” thus captures
the distribution of complex vector drawings on an implicit _set space_. We demonstrate the efficacy of our model on complex drawings (a newly created Anime
line-art dataset) through a range
of generative tasks.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: generative models

Submission Number: 1294