Original title: Human Machine Co-Creation. A Complementary Cognitive Approach to Creative Character Design Process Using GANs
Authors: Mohammad Lataifeh, Xavier A Carrascoa, Ashraf M Elnagara, Naveed Ahmeda, Imran Junejo
In this article, the author discusses recent advancements in Generative Adversarial Networks (GANs) and their applications. GANs are a type of neural network where two networks compete against each other to create new visual content that looks similar to the original dataset. The objective of this research is to create a collaborative process between humans and machines to enhance the abilities of character designers in visualizing and creating new characters for multimedia projects like games and animation. By using a combination of machine-generated concepts and human creativity, designers can come up with fresh ideas for characters. The author conducted experiments using a dataset of 22,000 characters and various GANs to find the most suitable approach. They also used mixed methods evaluation to assess both the machine-generated outputs and the human interpretations. The results demonstrate the effectiveness of this collaborative framework and how it influences the creative process of character conceptualization.
Original article: https://arxiv.org/abs/2311.13960