Outline Colorization through Tandem Adversarial Networks

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.

References in corpus (2)

• Conditional Generative Adversarial Nets
• Learning Representations for Automatic Colorization

Cited by in corpus (6)

• Real-Time User-Guided Image Colorization with Learned Deep Priors
• Joint Intensity-Gradient Guided Generative Modeling for Colorization
• LUCSS: Language-based User-customized Colourization of Scene Sketches
• The power of pictures: using ML assisted image generation to engage the crowd in complex socioscientific problems
• Line Art Correlation Matching Feature Transfer Network for Automatic Animation Colorization
• Interpreting Models by Allowing to Ask