Abstract
Generative AI has recently gained popularity as a paradigm for content generation. In this paper, we link this paradigm to an older one: Procedural Content Generation (PCG). We propose a lens to identify the commonalities between both paradigms that we call human-AI interactive generation. Using this lens, we identify three beneficial attributes then survey recent related work and summarize relevant findings.
Keywords
- Humans and AI: HAI: Human-computer interaction
- Machine Learning: ML: Generative models
- Multidisciplinary Topics and Applications: MTA: Computer games
- Humans and AI: HAI: Intelligent user interfaces
