MISS GAN: A Multi-IlluStrator style generative adversarial network for image to illustration translation

Unsupervised style transfer that supports diverse input styles using only one trained generator is a challenging and interesting task in computer vision. This paper proposes Multi-IlluStrator Style Generative Adversarial Network (MISS GAN) multi-style framework for unsupervised image-to-illustration translation, which can generate styled yet content preserving images. The illustrations dataset since it comprised of seven different illustrators, hence contains styles. Existing methods require to train several generators (as the number illustrators) handle illustrators' styles, limits their practical usage, or an image specific network, ignores information provided other images illustrator. MISS GAN both uses model.