Analysis and Application Research of Typical Technologies of Generative AI in the Context of Games

Shuzhao Shen

doi:10.62051/mps9h313

Authors

Shuzhao Shen

DOI:

https://doi.org/10.62051/mps9h313

Keywords:

Generative artificial intelligence; game development; programmatic content generation; dynamic narrative; human-computer interaction.

Abstract

With the rapid development of artificial intelligence technology, generative AI technology is gradually reshaping the paradigm of game development. It not only greatly improves the efficiency of game content generation, but also enhances the interactivity and personalized experience of games, which will be a unique new experience for developers and players. This paper focuses on the typical technical architecture and innovative applications of generative AI in the game field, and systematically analyzes the core principles, technical advantages and limitations of typical technologies such as GANs and Diffusion Models. It also derives innovative technologies in this field of generative AI in recent years, such as the PANGeA framework and the Text-to-Game engine. Through innovative technical research, this paper deeply explores the application efficiency of generative AI in scenarios such as character generation, dynamic narrative and code automation, and combines industrial practices such as Inworld AI Character Engine and Roblox's generative tool chain to reveal its potential in improving development efficiency and player immersion. This paper further points out that generative AI still faces challenges in terms of computing resource consumption, content controllability, ethical risks and cross-platform compatibility. In the future, with algorithm optimization and hardware iteration, generative AI is expected to drive the evolution of the gaming industry towards intelligence and personalization through adaptive content generation and multimodal interaction technology.

Downloads

Download data is not yet available.

References

[1] D. J. Yang, E. Kleinman, C. Harteveld, GPT for Games: A Scoping Review (2020-2023), IEEE Conference on Games (2024)

[2] X. Wang, H. J. Yuan, S. W. Zhang, D. Y. Chen, J. N. Wang, Y. Y. Zhang, Y. J. Shen, D. L. Zhao, J. R. Zhou, VideoComposer: Compositional Video Synthesis with Motion Controllability, https://doi.Org/10.48550/arXiv.23 06.02018 (2023)

[3] Z. Xing, Q. J. Feng, H. R. Chen, Q. Dai, H. Hu, H. Xu, Z. X. Wu, Y. G. Jiang, A Survey on Video Diffusion Models, https://doi.org/10.48550/arXiv.2310.10647 (2024)

[4] P. Y. Zhou, L. Wang, Z. Liu, Y. B. Hao, P. Hui, S. Tarkoma, J. Kangasharju, A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming, https://doi.org/10.48550/ arXiv. 2404.16038 (2024)

[5] Z. W. Wang, Q. She, T. E. Ward, Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy, ACM Computing Surveys (2020)

[6] P. Dhariwal, A. Nichol, Diffusion Models Beat GANs on Image Synthesis, Advances in Neural Information Processing Systems 34 (NeurIPS) (2021)

[7] Z. Y. Chang, G. A. Koulieris, H. P. H. Shum, On the Design Fundamentals of Diffusion Models: A Survey, https://doi.org/10.48550/arXiv.2306.04542 (2023)

[8] D. P. Kingma, M. Welling, Auto-Encoding Variational Bayes, https://doi.org/10.48550/arXiv.1312.6114 (2022)

[9] W. Q. Liu, R. Z. Li, M. Zheng, S. Karanam, Z. Y. Wu, B. Bhanu, R. J. Radke, O. Camps, Towards Visually Explaining Variational Autoencoders, CVPR (2020)

[10] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, I. Polosukhin, Attention Is All You Need, https://doi.org/10.48550/arXiv.1706.03762 (2023)

[11] J. Ratican, J. Hutson, Adaptive Worlds: Generative AI in Game Design and Future of Gaming, and Interactive Media, ISRG Journal of Arts Humanities & Social Sciences (ISRGJAHSS) (2024)

[12] S. Buongiorno, L. J. Klinkert, T. Chawla, Z. X. Zhuang, C. Clark, PANGeA: Procedural Artificial Narrative using Generative AI for Turn-Based Video Games, https://doi.org/10.48550/arXiv.2404.19721 (2024)

[13] L. Zhang, X. Z. Peng, S. Y. Yang, F. Y. Wang, A Text-to-Game Engine for UGC-Based Role-Playing Games, https://doi.org/10.48550/arXiv.2407.08195 (2025).