English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent advancements in implicit 3D representations and generative models havemarkedly propelled the field of 3D object generation forward. However, itremains a significant challenge to accurately model geometries with definedsharp features under parametric controls, which is crucial in fields likeindustrial design and manufacturing. To bridge this gap, we introduce aframework that employs Large Language Models (LLMs) to generate text-driven 3Dshapes, manipulating 3D software via program synthesis. We present 3D-PreMise,a dataset specifically tailored for 3D parametric modeling of industrialshapes, designed to explore state-of-the-art LLMs within our proposed pipeline.Our work reveals effective generation strategies and delves into theself-correction capabilities of LLMs using a visual interface. Our workhighlights both the potential and limitations of LLMs in 3D parametric modelingfor industrial applications.

3D-PreMise: Can Large Language Models Generate 3D Shapes with Sharp Features and Parametric Control?