Unsupervised Image to Sequence Translation with Canvas-Drawer Networks


Unsupervised Image to Sequence Translation with Canvas-Drawer Networks

Kevin Frans, Chin-Yi Cheng

Encoding images as a series of high-level constructs, such as brush strokes or discrete shapes, can often be key to both human and machine understanding. In many cases, however, data is only available in pixel form. We present a method for generating images directly in a high-level domain (e.g. brush strokes), without the need for real pairwise data. Specifically, we train a ”canvas” network to imitate the mapping of high-level constructs to pixels, followed by a high-level ”drawing” network which is optimized through this mapping towards solving a desired image recreation or translation task. We successfully discover sequential vector representations of symbols, large sketches, and 3D objects, utilizing only pixel data. We display applications of our method in image segmentation, and present several ablation studies comparing various configurations.

Download publication

Associated Researchers

Chin-Yi Cheng

Autodesk Research

Kevin Frans

Massachusetts Institute of Technology

View all researchers

Related Resources



Performing Incremental Bayesian Inference by Dynamic Model Counting

The ability to update the structure of a Bayesian network when new…



A Multi-Scale Stochastic Modelling Primitive for Computer Graphics

Stochastic modelling has been successfully used in computer graphics…



Configuration Design of Mechanical Assemblies using an Estimation of Distribution Algorithm and Constraint Programming

A configuration design problem in mechanical engineering involves…



3D Navigation

While advances in computing have empowered users to design and…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us