Generative Adversarial Networks for photo to Hayao Miyazaki style cartoons

TL;DR

This paper presents a GAN-based method trained on Miyazaki's artwork to convert photos into Miyazaki-style cartoons, outperforming existing style transfer techniques in cartoon-likeness.

Contribution

The study introduces a specialized GAN trained on Miyazaki's art to enhance photo-to-cartoon style transfer, demonstrating superior results over prior methods.

Findings

Our model outperforms state-of-the-art methods in cartoon-likeness.

Qualitative survey shows higher preference for our style transfer.

Training on over 60,000 Miyazaki images improves style authenticity.

Abstract

This paper takes on the problem of transferring the style of cartoon images to real-life photographic images by implementing previous work done by CartoonGAN. We trained a Generative Adversial Network(GAN) on over 60 000 images from works by Hayao Miyazaki at Studio Ghibli. To evaluate our results, we conducted a qualitative survey comparing our results with two state-of-the-art methods. 117 survey results indicated that our model on average outranked state-of-the-art methods on cartoon-likeness.