Automatic generation of graphical game assets using GAN
Rafal Karp, Żaneta Świderska-Chadaj · 2021
This paper presents an application of the Generative Adversarial Networks (GAN) approach to automatically generate realistic-looking fantasy and science fiction game icons. In this study, we explored ways to avoid the manual drawing of graphics, instead producing synthetic images indistinguishable from artist-made ones. We developed the method based on multiple experiments and commonly known GAN improvement techniques.