Generating Pixel Art Character Sprites using GANs

Abstract

Iterating on creating pixel art character sprite sheets is essential to the game development process. However, it can take a lot of effort until the final versions containing different poses and animation clips are achieved. This paper reports an investigation on the use of conditional generative adversarial networks to aid the designers in creating such sprite sheets. We propose an architecture based on Pix2Pix to generate images of characters facing a target side (e.g., right) given sprites of them in a source pose (e.g., front). Experiments with small pixel art datasets yielded promising results, producing models with varying degrees of generalization, sometimes capable of generating images very close to the ground truth. We analyzed the results through visual inspection and quantitatively with FID.