Worldwide Sites

You have been detected as being from . Where applicable, you can see country-specific product information, offers, and pricing.

Change country/language X

  • United States

    We have redirected you to an equivalent page on your local site where you can see local pricing and promotions and purchase online.

    Stay on our U.S. site

Keyboard ALT + g to toggle grid overlay

Unsupervised Image to Sequence Translation with Canvas-Drawer Networks

Kevin Frans, Chin-Yi Cheng

arXiv.org
2018

Abstract

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.

Related Publications

Related Projects

Heading

Descriptive text. Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt magna aliqua in reprehenderit.

Heading

Descriptive text. Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt magna aliqua in reprehenderit.

Heading

Descriptive text. Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt magna aliqua in reprehenderit.