Paper Dreams : an adaptive drawing canvas supported by machine learning

Abstract

Despite numerous recent advances in the field of deep learning for artistic purposes, the integration of these state-of-the-art machine learning tools into applications for drawing and visual expression has been an underexplored field. Bridging this gap has the potential to empower a large subset of the population, from children to the elderly, with a new medium to represent and visualize their ideas. Paper Dreams is a web-based canvas for sketching and storyboarding, with a multimodal user interface integrated with a variety of machine learning models. By using sketch recognition, style transfer, and natural language processing, the system can contextualize what the user is drawing; it then can color the sketch appropriately, suggest related objects for the user to draw, and allow the user to pull from a database of related images to add onto the canvas. Furthermore, the user can influence the output of the models via a serendipity dial that affects how "wacky" the system's outputs are. By processing a variety of multimodal inputs and automating artistic processes, Paper Dreams becomes an efficient tool for quickly generating vibrant and complex artistic scenes.