TRANSFORMING MODERN PARADIGMS OF 3D MODELING USING 3D GAUSSIAN SPLATTING METHODS
DOI:
https://doi.org/10.17721/3041-2323.2025.40-54Keywords:
3D scene reconstruction, real-time rendering, neural rendering, 3D Gaussian SplattingAbstract
This article examines 3D Gaussian Splatting (3D GS) —a novel and highly effective approach to real-time 3D scene reconstruction and rendering. 3D GS introduces an explicit, differentiable scene representation composed of millions of learnable 3D Gaussian elements. We describe the 3D GS workflow, from Structure-from-Motion–based initialization to iterative optimization and rendering. We also discuss its application potential across multiple domains, including monocular SLAM, RGB-D mapping, semantic reconstruction, and dynamic scene modeling. Comparative analysis shows that 3D GS achieves a compelling trade-off among visual quality, training time, and inference speed—outperforming both classical photogrammetric methods and prior neural rendering techniques on several benchmarks. These findings underscore 3D Gaussian Splatting as a transformative tool for modern 3D modeling tasks, particularly in scenarios requiring speed, editability, and scalability.
References
Arxiv.org. (2024). Stereo 3D Gaussian Splatting SLAM for Outdoor Urban Scenes. Отримано 29 вересня 2025 з https://arxiv.org/html/2507.23677v1.
Bernhard Kerbl, Kopanas, G., Leimkühler, T. and Drettakis, G. (2023). 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Transactions on Graphics, 42(4), pp.1–14. https://doi.org/10.1145/3592433.
Chen, S., Yuan, S., Nguyen, T.-M., Huang, Z., Shi, C., Jing, J. and Xie, L. (2025). EGS-SLAM: RGB-D Gaussian Splatting SLAM with Events. arXiv.org. Отримано 29 вересня 2025 з https://arxiv.org/abs/2508.07003.
Desboeufs, A. (н.д.). Point Sample Rendering. Отримано 29 вересня 2025 з https://cgl.ethz.ch/Downloads/Seminar_Arbeiten/1999/adesboeufs.pdf.
Drofova, I., Guo, W., Wang, H. and Adamek, M. (2023). Use of scanning devices for object 3D reconstruction by photogrammetry and visualization in virtual reality. Bulletin of Electrical Engineering and Informatics, 12(2), pp.868–881. https://doi.org/10.11591/eei.v12i2.4584.
Ebert, D. (2023). Introduction to 3D Gaussian Splatting. huggingface.co. Отримано 29 вересня 2025 з https://huggingface.co/blog/gaussian-splatting.
Fei, B., Xu, J., Zhang, R., Zhou, Q., Yang, W. and He, Y. (2024). 3D Gaussian Splatting as New Era: A Survey. IEEE Transactions on Visualization and Computer Graphics, pp.1–20. https://doi.org/10.1109/tvcg.2024.3397828.
Goesele, M., Ackermann, J., Fuhrmann, S., Klowsky, R., Langguth, F., Mücke, P. and Ritz, M. (2010). Scene Reconstruction from Community Photo Collections. Computer, 43(6), pp.48–53. https://doi.org/10.1109/mc.2010.176.
Gortler, S.J., Grzeszczuk, R., Szeliski, R. and Cohen, M.F. (1996). The lumigraph. Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques – SIGGRAPH ’96. https://doi.org/10.1145/237170.237200.
Hu, Y., Liu, R., Chen, M., Beerel, P. and Feng, A. (2025). SplatMAP: Online Dense Monocular SLAM with 3D Gaussian Splatting. Proceedings of the ACM on Computer Graphics and Interactive Techniques, 8(1), pp.1–18. https://doi.org/10.1145/3728310.
Ji, Y., Liu, Y., Xie, G., Ma, B., Xie, Z. and Liu, H. (2024). NEDS-SLAM: A Neural Explicit Dense Semantic SLAM Framework using 3D Gaussian Splatting. IEEE Robotics and Automation Letters, 9(10), pp.8778–8785. https://doi.org/10.1109/lra.2024.3451390.
Li, B., Hao, V.C., Stuckey, P.J., Reid, I. and Rezatofighi, H. (2025). Hier-SLAM++: Neuro-Symbolic Semantic SLAM with a Hierarchically Categorical Gaussian Splatting. arXiv.org. Отримано 29 вересня 2025 з https://arxiv.org/abs/2502.14931.
Matsuki, H., Murai, R., Paul, K. and Davison, A.J. (2025). Gaussian Splatting SLAM. arXiv.org. Отримано 29 вересня 2025 з https://arxiv.org/abs/2312.06741
Mildenhall, B., Srinivasan, P., Tancik, M., Barron, J., Ramamoorthi, R. and Ng, R. (2020). NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. Отримано 29 вересня 2025 з https://arxiv.org/pdf/2003.08934.
Niemeyer, M., Manhardt, F., Rakotosaona, M.-J., Oechsle, M., Duckworth, D., Gosula, R., Tateno, K., Bates, J., Kaeser, D. and Tombari, F. (2024). RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS. arXiv.org. https://doi.org/10.48550/arXiv.2403.13806.
Scianna, A. and La Guardia, M. (2019). Survey and Photogrammetric Restitution of Monumental Complexes: Issues and Solutions—The Case of the Manfredonic Castle of Mussomeli. Heritage, 2(1), pp.774–786. https://doi.org/10.3390/heritage2010050.
Snavely, N., Seitz, S. and Szeliski, R. (н.д.). Photo Tourism: Exploring Photo Collections in 3D. Отримано 29 вересня 2025 з https://phototour.cs.washington.edu/Photo_Tourism.pdf.
Tancik, M., Weber, E., Ng, E., Li, R., Yi, B., Kerr, J., Wang, T., Kristoffersen, A., Austin, J., Salahi, K., Ahuja, A., McAllister, D. and Kanazawa, A. (2023). Nerfstudio: A Modular Framework for Neural Radiance Field Development. arXiv (Cornell University). https://doi.org/10.1145/3588432.3591516.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Applied Information Systems and Technologies in the Digital Society
This work is licensed under a Creative Commons Attribution 4.0 International License.
