GENERATIVE AI AS A TOOL FOR TRANSFORMING DIGITAL INFORMATION INTO 3D GEOMETRY
Keywords:
generative artificial intelligence, 3D modeling, 3D printing, graphic communication.Abstract
The paper analyzes the use of generative artificial intelligence for the automatic generation of three-dimensional QR code models for additive manufacturing. The study starts from the limitations encountered in the direct generation of 3D files through natural language instructions, such as inconsistency of results, topological errors and incompatibilities with slicing software used in multi material 3D printing. Following an iterative process of refining the prompts and analyzing the errors, a universal Python code is developed, capable of reproducibly generating correct 3D QR code models by materials. The results show a significant increase in the success rate, from approximately 40–50% in the initial phase to over 90% after optimization, with fully functional and scannable models.
Downloads
References
ENCES
Daareyni, A., A. Martikkala, H. Mokhtarian, and I.
F. Ituarte, (2025), Generative AI meets CAD:
enhancing engineering design to manufacturing
processes with large language models, The
International Journal of Advanced Manufacturing
Technology, doi: 10.1007/s00170-025-15830-2.
Zhang, L., B. Le, N. Akhtar, S.-K. Lam, and D. Ngo,
(2026), Large Language Models for Computer
Aided Design: A Survey, ACM Comput. Surv., vol.
, no. 9, p. Article 225, Art no., doi:
1145/3787499.
JOURNAL OF INDUSTRIAL DESIGN AND ENGINEERING GRAPHICS 141
Generative AI as a Tool for Transforming Digital Information into 3D Geometry
Dori, D. and K. Tombre, (1995), From engineering
drawings to 3D CAD models: are we ready now?,
Computer-Aided Design, vol. 27, no. 4, pp. 243–254,
Art
no.
[Online].
Available:
https://www.sciencedirect.com/science/article/pii/00
Jakub, K., M. Aleksandra, M. Dariusz, and Rojek,
(2024), Enhancing 3D Printing with Procedural
Generation and STL Formatting Using Python,
Applied Sciences, vol. 14, no. 16, p. 7299, Art no.
[Online]. Available: https://www.mdpi.com/2076
/14/16/7299.
Peckham, O. et al., (2025), Artificial Intelligence in
Generative Design: A Structured Review of Trends
and Opportunities in Techniques and Applications,
Designs, vol. 9, no. 4, p. 79, Art no. [Online].
Available:
/9/4/79.
ISO/IEC 18004:2015 Information technology —
Automatic
identification
and data capture
techniques — QR Code bar code symbology
specification, International Organization for, S.,
Geneva, Switzerland, 2015.
Mititelu, N.-R. and et al., (2025), Use of AI
Language Models in Generating 3D Printable
Models, Acta Technica Napocensis - Series: Applied
Mathematics, Mechanics, and Engineering, vol. 68,
no.
S.
[Online].
Available:
https://atna
mam.utcluj.ro/index.php/Acta/article/view/2779.
Shafiq, O., A. Rahmat, A. Alexiadis, and B. Ghiassi,
"Evaluating the Performance of Large Language
Models for Geometry and Simulation File
Generation in Physics-Based Simulations," Applied
Sciences,
vol.
,
no. 22, p. 12114doi:
3390/app152212114.
Guan, Y., X. Wang, X. Xing, J. Zhang, D. Xu, and
Q. Yu, (2025), CAD-Coder: Text-to-CAD
Generation with Chain-of-Thought and Geometric
Reward, arXiv preprint arXiv:2505.19713.
Picard, C. et al., (2025), From concept to
manufacturing: evaluating vision-language models
for engineering design, Artificial Intelligence
Review, vol. 58, no. 9, p. 288, Art no., doi:
1007/s10462-025-11290-y.
Mititelu, N. R., (2024), Theoretical aspects regarding
AI implementation in optimized STL file generation,
International journal of engineering research &
technology (IJERT), vol. 13.
Deng, H., S. Khan, and J. A. Erkoyuncu, (2024), An
Investigation on Utilizing Large Language Model
for Industrial Computer-Aided Design Automation,
Procedia CIRP, vol. 128, pp. 221-226, Art no., doi:
https://doi.org/10.1016/j.procir.2024.07.049.
Mititelu N. R, Hobjala R., and P. C., (2024), THE
USE OF ARTIFICIAL INTELLIGENCE FOR
DETECTING AND SOLVING PRINTING ISSUES
TEHNOMUS - New Technologies and Products in
Machine Manufacturing Technologies vol. 31.
Haque, S., M. H. Tanveer, and R. C. Voicu,(2025),
"AI-Driven 3D Printing: Generative Gcode for
Quality and Efficiency," in SoutheastCon 2025, 22
March 2025 2025, pp. 1282-1287, doi:
1109/SoutheastCon56624.2025.10971689.
Paviot, T., V. Fortineau, and S. Lamouri, (2025),
Iterative Diagnosis-Driven Augmented Generation
(IDDAG) for Programmatic 3D CAD. [Online].
Available:
https://www.scitepress.org/Papers/2025/134435/134
pdf.
Mititelu, N.-R., M. Nicolau, A. I. Irimia, and C.-G.
Gradinariu, (2026), Methodological Framework for
Evaluating the Generative Capabilities of AI
Assisted CAD Parametric Modeling for AM,
Materials Research Proceedings, vol. 61, pp. 77-83,
Art no.
Ermolai, V. et al., (2024), XYZ Calibration Cube –
A Misleading Tool for Achieving Print Accuracy,
Materials Research Proceedings, vol. 46, pp. 23-34,
Art no.
Fudos, I. et al., (2020), A characterization of 3D
Printability, arXiv preprint arXiv:2010.12930.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
