toon2real: Translating Cartoon Images to Realistic Images

TL;DR

This paper introduces a CycleGAN-based method with spectral normalization to effectively translate cartoon images into realistic photos, outperforming existing models in quality and stability.

Contribution

The paper proposes a novel approach combining CycleGAN and spectral normalization for improved cartoon-to-realistic image translation.

Findings

Achieved lowest Frechet Inception Distance score.

Produced higher quality translations than state-of-the-art models.

Enhanced model stability with spectral normalization.

Abstract

In terms of Image-to-image translation, Generative Adversarial Networks (GANs) has achieved great success even when it is used in the unsupervised dataset. In this work, we aim to translate cartoon images to photo-realistic images using GAN. We apply several state-of-the-art models to perform this task; however, they fail to perform good quality translations. We observe that the shallow difference between these two domains causes this issue. Based on this idea, we propose a method based on CycleGAN model for image translation from cartoon domain to photo-realistic domain. To make our model efficient, we implemented Spectral Normalization which added stability in our model. We demonstrate our experimental results and show that our proposed model has achieved the lowest Frechet Inception Distance score and better results compared to another state-of-the-art technique, UNIT.