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
Learned Visual Features to Textual ExplanationsA novel method that leverages the capabilities of large language…
2023
Autodesk Research Celebrates International Women in Engineering DayIn celebration of International Women in Engineering Day, we talk with…
2015
Meltables: Fabrication of Complex 3D Curves by MeltingWe propose a novel approach to fabricating complex 3D shapes via…
2022
AvatAR: An Immersive Analysis Environment for Human Motion Data Combining Interactive 3D Avatars and TrajectoriesAnalysis of human motion data can reveal valuable insights about the…
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