toon2real: Translating Cartoon Images to Realistic Images
This addresses a domain-specific image translation challenge for applications in media and entertainment, but it is incremental as it builds on existing GAN frameworks.
The paper tackles the problem of translating cartoon images to realistic images using a modified CycleGAN with Spectral Normalization, achieving the lowest Frechet Inception Distance score compared to state-of-the-art methods like UNIT.
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.