CVNov 28, 2018

Cartoon-to-real: An Approach to Translate Cartoon to Realistic Images using GAN

arXiv:1811.11796v32 citations
Originality Synthesis-oriented
AI Analysis

This addresses a domain-specific image translation task for applications in media or entertainment, but it is incremental as it applies existing methods like CycleGAN to a new dataset.

The paper tackled the problem of translating cartoon images to realistic images using a GAN-based method, specifically CycleGAN, to handle unpaired datasets, and demonstrated that the model generates meaningful real-world images, with performance compared to Deep Analogy.

We propose a method to translate cartoon images to real world images using Generative Aderserial Network (GAN). Existing GAN-based image-to-image translation methods which are trained on paired datasets are impractical as the data is difficult to accumulate. Therefore, in this paper we exploit the Cycle-Consistent Adversarial Networks (CycleGAN) method for images translation which needs an unpaired dataset. By applying CycleGAN we show that our model is able to generate meaningful real world images from cartoon images. However, we implement another state of the art technique $-$ Deep Analogy $-$ to compare the performance of our approach.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes