What is it about?
Photo cartoonization aims to convert photos of real-world scenes into cartoon-style images. Recently, generative adversarial network (GAN)-based methods for photo cartoonization have been proposed to generate pleasable cartoonized images. However, as these methods can transfer only learned cartoon styles to photos, they are limited in general-purpose applications where unlearned styles are often required. In this paper, to solve this problem, we propose a novel arbitrary-style photo cartoonization method, Cartoon-Flow. More specifically, we construct a new hybrid GAN with an invertible neural flow generator to effectively preserve content information. In addition, we introduce two new losses for cartoonization
Featured Image
Photo by Erik Mclean on Unsplash
Why is it important?
We propose Cartoon-Flow, a hybrid generative adversarial network for arbitrary-style photo cartoonization. In addition, to generate high-quality cartoon images, we introduce two novel loss functions: (1) an edge-promoting smooth loss for smooth surfaces and clear edges, and (2) a line loss to mimic the line drawing of cartoons. This paper will be useful for both cartoonists and researchers who seek to further explore the use of AI for cartoons.
Perspectives
It was a great pleasure to write this paper. I hope this paper will help people make cartoons more efficient and easier.
Jieun Lee
Korea University
Read the Original
This page is a summary of: Cartoon-Flow: A Flow-Based Generative Adversarial Network for Arbitrary-Style Photo Cartoonization, October 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3503161.3548094.
You can read the full text:
Contributors
The following have contributed to this page
