Cross-Domain Style Mixing for Face Cartoonization
This addresses the problem of creating diverse cartoon faces with minimal data for artists and content creators, though it appears incremental over prior layer swapping methods.
The paper tackles the challenge of face cartoonization by proposing Cross-domain Style Mixing, which stylizes faces into multiple cartoon characters at various abstraction levels using only a single generator and limited training images.
Cartoon domain has recently gained increasing popularity. Previous studies have attempted quality portrait stylization into the cartoon domain; however, this poses a great challenge since they have not properly addressed the critical constraints, such as requiring a large number of training images or the lack of support for abstract cartoon faces. Recently, a layer swapping method has been used for stylization requiring only a limited number of training images; however, its use cases are still narrow as it inherits the remaining issues. In this paper, we propose a novel method called Cross-domain Style mixing, which combines two latent codes from two different domains. Our method effectively stylizes faces into multiple cartoon characters at various face abstraction levels using only a single generator without even using a large number of training images.