From Prompts to Worlds: How Users Iterate, Explore, and Make Sense of AI-Generated 3D Environments

Researchers conducted the first empirical study of commercial text-to-3D AI platforms, finding that users can convey semantic themes but struggle with spatial structure specification. The study reveals interaction barriers including poor discoverability and high iteration costs that limit the effectiveness of current text-to-3D systems.

• →Users can easily express semantic intent like themes and atmosphere but struggle to specify spatial structure and layout in text-to-3D systems.
• →Immersion in AI-generated 3D environments occurs episodically when expectations align with outputs but doesn't sustain long-term presence.
• →Current text-to-3D systems suffer from poor discoverability, opaque feedback, and high temporal costs that prevent effective iteration.
• →Researchers recommend hybrid input modalities and transparent feedback mechanisms for more effective text-to-3D platforms.
• →The study reframes text-to-3D interaction as negotiated meaning-making rather than simple linear prompting.