3D Scene Reconstruction of Architectural Engineering Based on 3D Gaussian Splatting
DOI:
https://doi.org/10.54691/k2rrnc91Keywords:
3D reconstruction, UAV, radiation field, 3D gaussian.Abstract
In order to solve the problems of high time cost, poor rendering quality and low efficiency of manual maintenance in the field of engineering and architecture, a novel method combining 3D Gaussian algorithm for real-world reconstruction was proposed. The method uses UAV aerial photography for data collection, and uses point cloud data for reconstruction, which realizes the real-time rendering of the radiation field, which provides a significant acceleration for scene optimization and novel view synthesis. It greatly improves the efficiency and accuracy in the field of construction engineering.
Downloads
References
[1] Ji.H.Y,He.Y.M,Zhang.W.J,Wu.H, Research on urban 3D reconstruction technology based on unmanned aerial vehicle oblique photogrammetry point cloud data [J] Automation and Instrumentation,2024, (09): 330-333+338.
[2] Mohd Isa S N, Abdul Shukor S A, Rahim N A, et al. A review of data structure and filtering in handling 3D big point cloud data for building preservation [C] ∥ 2018 IEEE Conference on Systems, Process and Control ( ICSPC) , 2018: 141-146.
[3] Wang.M,Yan.K,Luo.X,etc, Research and Application of Preprocessing Technology Based on 3D Point Cloud Data [J] Power Big Data,2024,27(09):61-68.DOI:10.19317/j.cnki.1008-083x.2024.09.007.
[4] SUN Jinhu. Research on key technologies of point cloud segmentation and fusion [D] . Nanjing: Nanjing University of Aeronautics and Astronautics, 2013.
[5] Zhang.W.L, Research on Grid Technology of 3D Point Cloud Data [D] Changchun: Changchun University of Technoogy University of Technology, 2023. DOI:10.27805/d.cnki.gccgy.2023.000696.
[6] Tan.C, Neural network-based triangular mesh simplification algorithm [D] Hefei: University of Science and Technology of China,2022.DOI:10.27517/d.cnki.gzkju.2022.002141.
[7] Debevec P E, Taylor C J, Malik J. Modeling and rendering architecture from photographs: a hybrid geometry-and image-based approach [C] ∥Proceedings of the 23rd annual Conference on Computer Graphics and Interactive Techniques, 1996: 11-20.
[8] Chen X, Wu Q F, Wang S Z. Research on 3D reconstruction based on multiple views [C] ∥2018 13th International Conference on Computer Science＆Education ( ICCSE), 2018: 1-5.
[9] Lowe D G. Object recognition from local scale-invariant features [C] ∥Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999. DOI: 10. 1109 /ICCV. 1999. 790410.
[10] Lowe D G. Distinctive image features from scale-invariant key points [J] . International Journal of Computer Vision, 2004, 60( 2) : 91-110.
[11] Gallup D, Frahm J M, Mordohai P, et al. Real-time planesweeping stereo with multiple sweeping directions [C] ∥ IEEE Conference on Computer Vision and Pattern Ｒecognition, 2007. DOI: 10. 1109 /CVPＲ. 2007. 383245.
[12] Bleyer M, Rhemann C, Rother C. PatchMatch stereostereo matching with slanted support windows [C] ∥ British Machine Vision Conference, 2011.
[13] Huang P H, Matzen K, Kopf J, et al. DeepMVS: learning multi-view stereopsis [C] ∥ IEEE Conference on Computer Vision and Pattern Ｒecognition, 2018: 2821-2830.
[14] Fridovich-Keil and Yu, Matthew Tancik, Qinhong Chen, Benjamin Recht, and Angjoo Kanazawa. 2022. Plenoxels: Radiance Fields without Neural Networks. In CVPR.
[15] Mao.B.Y,Zhang.W,Liang.Z.Q,Peng.Q.Y,Wang.Y,Wang.Y.X, The application process, principles, and examples of drone photogrammetry and 3D reconstruction technology in the field of architecture [J] Huazhong Architecture, 2024, 42 (09): 53-59.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Frontiers in Science and Engineering
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
