Interactive Cartoonization with Controllable Perceptual Factors

TL;DR

This paper introduces a novel deep cartoonization method that allows users to control texture and color attributes during inference, improving editability and diversity of generated cartoons.

Contribution

It proposes a new model architecture with separate decoders for texture and color, including a texture controller and HSV augmentation for enhanced controllability and quality.

Findings

Enables user control over stroke style and abstraction.

Achieves diverse and controllable color translation.

Shows significant quality improvements over baseline methods.

Abstract

Cartoonization is a task that renders natural photos into cartoon styles. Previous deep cartoonization methods only have focused on end-to-end translation, which may hinder editability. Instead, we propose a novel solution with editing features of texture and color based on the cartoon creation process. To do that, we design a model architecture to have separate decoders, texture and color, to decouple these attributes. In the texture decoder, we propose a texture controller, which enables a user to control stroke style and abstraction to generate diverse cartoon textures. We also introduce an HSV color augmentation to induce the networks to generate diverse and controllable color translation. To the best of our knowledge, our work is the first deep approach to control the cartoonization at inference while showing profound quality improvement over to baselines.