ImoGenXR : Investigating the Impact on Creativity Support in a Generative-AI Assisted Immersive Authoring Workflow

Limbert, George and Karnik, Abe (2025) ImoGenXR : Investigating the Impact on Creativity Support in a Generative-AI Assisted Immersive Authoring Workflow. In: 2025 the 11th International Conference on Virtual Reality Wageningen, Netherlands : ICVR 2025. IEEE, pp. 1-10. (In Press)

Text (VR1013)
VR1013.pdf - Accepted Version
Restricted to Repository staff only until 9 July 2025.
Available under License Creative Commons Attribution-NonCommercial-ShareAlike.
Download (2MB)

Abstract

Creating interactive extended reality experiences is currently a complex activity with a high entry barrier of developer skills. Immersive authoring and no/low code techniques are a promising direction towards democratizing access to novice users as they lower the entry barrier while users develop advanced skills. Similarly, generative-AI has shown potential for template code generation, 3D model creation and retrieval. In this paper, we present ImoGenXR, an immersive workflow integrated with Unity and scaffolded by existing generative-AI. Users can build scenes within the immersive environment by inserting 3D models using voice commands. They can also attach AI-generated code to invoke desired behaviours without leaving the immersive environment. We use ImoGenXR’s workflow to explore the effect of creativity support using generative AI on an existing tool like Unity. The results show significant improvement in user experience for novice users. ImoGenXR shows the value of including creativity support through generative AI for existing XR development tools.