Semantic Weaponry: A Modular Approach to Text-to-3D Model generation
Authors: Lower, T., Anderson, E.F.
Conference: Eurographics 2026
Dates: 04/05/2026
Journal: Eurographics 2026
Publication Date: 04/05/2026
Volume: EG 2026 - Posters
Publisher: The Eurographics Association
Place of Publication: Aachen, Germany
ISBN: 978-3-03868-300-1
ISSN: 1017-4656
DOI: 10.2312/egp.20261006
Abstract:We present a modular approach to AI-assisted Text-to-3D content generation that takes a semantic description of a 3D model, leveraging the semantic capabilities of Large Language Models to create a set of parameters which are then fed into an implicit surface function. The resulting geometry can be remeshed for use in 3D Digital Content Creation applications.
https://eprints.bournemouth.ac.uk/41955/
Source: Manual