A Systematic Literature Review of Generative Adversarial Network Potential In AI Artwork

Humans have studied calligraphy and calculated programs to foster creativity for years. Image generation technology using artificial intelligence and Generative Adversarial Networks is currently reaching the peak of its performance. While there are newer and newer algorithms to improve the image generation system, the output of the images is still suitable at best and only excels in their category. While it is true that some of the images generated are good enough to be used, it is still unclear whether the capabilities of AI image generation can outperform their creative human counterparts. Therefore, this literature study aims to explore the basics of AI image generation, how they work, and what factors contribute to creating art such as simple pictures. Previous studies from several years ago show that most generated images are not good enough for creative usage because they only replicate traces of their dataset. The most significant factor contributing to this is the algorithm used and how it is used to create new images. In general, the concluded that while current AI-generated images are improving, they are still not creative enough to replace human creativity.