Interactive Cartoonization with Controllable Perceptual Factors
This work addresses the need for more interactive and controllable cartoonization tools for artists and designers, though it is incremental in enhancing existing deep learning approaches.
The paper tackles the problem of limited editability in deep cartoonization methods by proposing a model with separate texture and color decoders, enabling user control over stroke style, abstraction, and color, resulting in improved quality over baselines.
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.