Application of Neural Network in Pixel Art Creation: Bi-directional Conversion between Photo and Pixel Art with GAN Base Model

Pixel art was first developed in the last century when computers have limited memory and processing power, and is in wide use in the game industry now. However, pixel art is a highly stylized art form that requires skilled human artists to create and the creation process is time consuming. This paper proposes an automatic way to convert photos to pixel drawings and the reverse with unsupervised, GAN based neural networks.