Research on Intelligent 3D Modeling and Rendering and Application Analysis

Fengyuan Liu

doi:10.62051/necnrf10

Authors

Fengyuan Liu

DOI:

https://doi.org/10.62051/necnrf10

Keywords:

3D Modeling, Artificial Intelligence (AI), Rendering Engines, Hybrid Systems.

Abstract

This paper investigates the evolution of 3D modeling and rendering technologies, from traditional manual techniques to Artificial Intelligence (AI)-assisted processes. It explores the transition from time-intensive manual modeling to procedural and AI-based approaches, highlighting the impact of artificial intelligence in automating and enhancing the modeling process. The study also examines modern rendering engines, discussing integrating real-time performance with visual fidelity, focusing on technologies like ray tracing and AI-optimized hybrid systems. A two-part methodology is proposed: the first part analyzes various modeling platforms, including manual, procedural, and AI-based approaches, while the second part assesses rendering engines. Key tools such as Dream Fusion and Unreal Engine 5 are reviewed, identifying their technical principles and limitations. The study finds that although AI offers significant advantages in scalability and automation, it still faces challenges in controllability, precision, and hardware dependence. The paper proposes future research on AI-human collaborative frameworks and lightweight modeling systems to improve generation efficiency, reduce hardware costs, and enhance user-driven customization. This research comprehensively overviews current developments and future directions in intelligent 3D modeling and rendering technologies.

Downloads

Download data is not yet available.

References

[1] MUNSTER Sander, et al. Handbook of digital 3D reconstruction of historical architecture. Springer Nature, 2024, 204.

[2] DI Stefano, FRANCESCO, et al. Mobile 3D scan LiDAR: A literature review. Geomatics, natural hazards and risk, 2021, 12(1): 2387-2429.

[3] SADEGHI Amir, et al. Current and future applications of virtual, augmented, and mixed reality in cardiothoracic surgery. The Annals of thoracic surgery, 2022, 113(2): 681-691.

[4] HAUTANEN Julia. Proseduraalinen mallintaminen 3D-tuotannossa. porrastyökalun luonti Houdini-ohjelmalla. 2022, 1-50.

[5] KELLY Tom. CityEngine: An introduction to rule-based modeling. Urban informatics, 2021, 637-662.

[6] YANG Karren, et al. Probabilistic speech-driven 3D facial motion synthesis: new benchmarks methods and applications. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024, 27294-27303.

[7] MENGISTU Biruk. Deep-Learning Realtime Upsampling Techniques in Video Games. Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal, 2023, 10(2): 4.

[8] Yu Alex, et al. pixelnerf: Neural radiance fields from one or few images. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, 4578-4587.

[9] KIM Youngwook, YUNMIN Ko, and INSGUNG Ihm. Selective foveated ray tracing for head-mounted displays. IEEE International Symposium on Mixed and Augmented Reality (ISMAR). 2021, 413-421.

[10] POOLE Ben, et al. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988, 2022.

[11] TAN Tiow Wee. Mastering Lumen Global Illumination in Unreal Engine 5. Game Development with Unreal Engine 5, 2024, 1: 223-275.

[12] BEBESHKO B., et al. 3D modelling by means of artificial intelligence. Journal of Theoretical and Applied Information Technology, 2021, 99(6): 1296-1308.

[13] LIANG Jia Yuan, SHAN Xin Yi, and CHUNG Jeanhun. A Study on Process of Creating 3D Models Using the Application of Artificial Intelligence Technology. International Journal of Advanced Culture Technology. 2023, 11(4): 346-351.