Evolving Camouflages: A User-Centric AI Approach for Game Aesthetics

Artificial intelligence (AI) can create icons, skins, and camouflages for games. An optimal implementation of such a concept might provide new and more advanced features that benefit the user experience. This project investigates the use of an evolutionary algorithm for texture generation and allows users to choose and manipulate camouflage patterns. This enables users to create camouflage patterns that could theoretically be implemented in a video game. This study is supported by user testing to gather insight into usability and the users’ ability to replicate a target pattern. The result is an evaluation of gathered data showing user tendencies and how they engage with the system. These tendencies include significantly different completion times for target patterns varying in complexity. Additionally, participants mostly agreed that the tool is helpful for future games and objects other than camouflage skins. The findings suggest potential applications for AI in enhancing user customization and design flexibility. Further research is needed to address technical limitations and explore broader game industry implications. A brief introduction to the system described in this paper was published as a short paper in the IEEE Conference on Game (CoG) (Ploug et al. 2024).