Outline Colorization through Tandem Adversarial Networks

TL;DR

This paper introduces a tandem adversarial network approach for automatic digital outline colorization, combining color prediction and shading networks to produce realistic results from line art and user-defined color schemes.

Contribution

It presents a novel tandem network architecture with processing techniques for better generalization in outline colorization tasks.

Findings

Produces natural-looking colorized outlines from scratch

Handles messy, user-defined color schemes effectively

Improves generalization through processing methods

Abstract

When creating digital art, coloring and shading are often time consuming tasks that follow the same general patterns. A solution to automatically colorize raw line art would have many practical applications. We propose a setup utilizing two networks in tandem: a color prediction network based only on outlines, and a shading network conditioned on both outlines and a color scheme. We present processing methods to limit information passed in the color scheme, improving generalization. Finally, we demonstrate natural-looking results when colorizing outlines from scratch, as well as from a messy, user-defined color scheme.