Publication
Unsupervised Image to Sequence Translation with Canvas-Drawer Networks
Abstract
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 publicationAssociated Researchers
Chin-Yi Cheng
Autodesk Research
Kevin Frans
Massachusetts Institute of Technology
Related Resources
2023
Leading the Way in Design and Make: Autodesk Researchers at AU
Explore what Autodesk Researchers will be presenting at Autodesk…
2023
Recently Published by Autodesk Researchers
A selection of recently published papers by Autodesk Researchers…
2004
Regularizing a singular special Lagrangian variety
Consider two special Lagrangian submanifolds with boundary in…
2023
Girl Gang Garage’s Volvo Restoration Inspires Next Generation of Technicians
How Girl Gang Garage uses Fusion 360 for a vehicle mash-up. …
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