Outline Colorization through Tandem Adversarial Networks
This addresses a practical problem for digital artists by automating repetitive coloring and shading patterns, though it appears incremental as it builds on existing adversarial network methods.
The paper tackled the problem of automatically colorizing raw line art to reduce time-consuming manual coloring and shading tasks, achieving natural-looking results from both scratch outlines and messy user-defined color schemes.
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.