Unsupervised Image to Sequence Translation with Canvas-Drawer Networks
This addresses the challenge of unsupervised image-to-sequence translation for tasks like image segmentation, though it appears incremental as it builds on existing unsupervised methods.
The paper tackles the problem of generating images from high-level constructs like brush strokes without paired data, by training a canvas network to map constructs to pixels and a drawing network for image recreation, achieving sequential vector representations of symbols, sketches, and 3D objects using only pixel data.
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.