APPLICATION OF ARTIFICIAL INTELLIGENCE IN 3D MODELING BASED ON BLENDER

Authors

DOI:

https://doi.org/10.28925/2663-4023.2025.31.1071

Keywords:

computer graphics, 3D modeling, Blender, artificial intelligence, neural networks, automation.

Abstract

The article explores the prospects for applying artificial intelligence methods in the field of 3D modeling using the Blender software environment. Modern approaches to integrating AI algorithms into the processes of creating three-dimensional objects, materials, and scenes are considered, including automated geometry generation, texture creation, topology optimization, and acceleration of routine modeling stages. The capabilities of using neural network models in combination with built-in Blender tools and its API are analyzed, and key directions for the development of plugins and external services focused on AI-assisted 3D graphics are outlined. Special attention is paid to the impact of artificial intelligence on the productivity of 3D artists and to the transformation of the user’s role from direct manual modeling to managing generation parameters and evaluating generated results. The research findings can be applied both in the educational process of the “Computer Graphics” discipline and in practical projects within the game industry, VR/AR technologies, and digital design. The article also addresses limitations and challenges associated with the use of artificial intelligence in 3D modeling, including issues related to the quality of generated models, result control, computational resource requirements, and the integration of AI tools into standard production pipelines. Existing approaches to combining traditional computer graphics methods with generative models are generalized, enabling the identification of promising directions for further research in this field. It is concluded that the use of artificial intelligence in Blender opens new opportunities for improving the efficiency of 3D modeling education and contributes to the transformation of digital content creation approaches in the context of the modern digital economy.

Downloads

Download data is not yet available.

References

Foley, J. D., van Dam, A., Feiner, S. K., & Hughes, J. F. (2014). Computer graphics: Principles and practice (3rd ed.). Addison-Wesley.

Nadkernychna, T. M., et al. (n.d.). 3D modeling in the Blender software.

Zolotov, A. V. (n.d.). Features of using Blender 3D in the educational process.

Mosiichuk, O. M. (n.d.). Methodological aspects of studying 3D modeling in higher education.

Shevchenko, L. S. (n.d.). The use of artificial intelligence technologies in the training of designers.

Poole, B., Jain, A., Barron, J. T., & Mildenhall, B. (2022). DreamFusion: Text-to-3D using 2D diffusion. arXiv. https://arxiv.org/abs/2209.14988

Ding, L., et al. (2024). Text-to-3D generation with bidirectional diffusion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024).

Yang, X., et al. (2024). Diverse and stable text-to-3D generation. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2024).

Jun, H., & Nichol, A. (2023). Shap-E: Generating conditional 3D implicit functions. arXiv. https://arxiv.org/abs/2305.02463

Kerbl, B., et al. (2023). 3D Gaussian splatting for real-time radiance field rendering. arXiv. https://arxiv.org/abs/2308.04079

Denninger, M., et al. (2019). BlenderProc: A procedural pipeline for photorealistic rendering. arXiv. https://arxiv.org/abs/1911.01911

Denninger, M., et al. (2023). BlenderProc2: A procedural pipeline for photorealistic rendering. Journal of Open Source Software, 8(84), 5104. https://doi.org/10.21105/joss.05104

Downloads


Abstract views: 7

Published

2025-12-16

How to Cite

Bobryshev, Y. (2025). APPLICATION OF ARTIFICIAL INTELLIGENCE IN 3D MODELING BASED ON BLENDER. Electronic Professional Scientific Journal «Cybersecurity: Education, Science, Technique», 3(31), 741–751. https://doi.org/10.28925/2663-4023.2025.31.1071