Description
The field of 3D model generation is rapidly advancing, driven by the increasing interest in generative Artificial Intelligence. Various tools can now transform text and images into 3D content, facilitating the creation of procedural geometry and opening new avenues for prototyping and design. This thesis aims to develop an immersive Virtual Reality environment that allows users to generate 3D content through a voice interface. Additionally, Large Language Models will be used to enhance prompting capabilities and enable more sophisticated and context-aware interactions, leading to improved user experiences.
Tasks
- Develop the framework to generate 3D models
- Analyze existing services for 3D model creation
- Run a user study to evaluate the system
Requirements
- Knowledge of English language (source code, comments, and final report should be in English)
- Programming skills (especially C++ or UE5 Blueprints)
- Knowledge of VR is advantageous
Environment
The project will be developed using Unreal Engine 5 and deployed to a head-mounted display – either the Meta Quest 2 or the HTC Vive.
Contact
For more information please contact Matteo Bosco – matteo.bosco@tuwien.ac.at