Anime Illustration Colorization with Deep Learning

There are a lot of different deep learning models out there that can be used for learning colorization mapping. In this project, I am going to use Pix2Pix to solve the problem. We will use a U-Net and a PatchGAN as the generator and the discriminator respectively as proposed in the Pix2Pix paper. The Pix2Pix model is a GAN, or specifically, it is a type of conditional GAN (cGAN). Just like a GAN, Pix2Pix trains the generator and the discriminator simultaneously. But instead of taking samples from a latent space, the Pix2Pix generator takes images as inputs.