Reconstruction of Building LIDAR Point Cloud Based on Geometric Primitive Constrained Optimization
Source abstract
Abstract
This study proposes a 3D reconstruction method for LIDAR building point clouds using geometric primitive constrained optimization. It addresses challenges such as low accuracy, high complexity, and slow modeling. This new algorithm studies the reconstruction of point clouds at the level of geometric primitives and is an incremental joint optimization method based on the GPU rendering pipeline. Firstly, the building point cloud collected by the LIDAR laser scanner was preprocessed, and an initial building mesh model was constructed by the fast triangulation method. Secondly, based on the geometric characteristics of the building, geometric primitive constrained optimization rules were generated to optimize the initial mesh model (regular surface optimization, basis spline surface optimization, junction area optimization, etc.). And a view-dependent parallel algorithm was designed to optimize the calculation. Finally, the effectiveness of this approach was validated by comparing and analyzing the experimental results of different buildings’ point cloud data. This algorithm does not require data training and is suitable for outdoor surveying and mapping engineering operations. It has good controllability and adaptability, and the entire pipeline is interpretable. The obtained results can be used for serious applications, such as Building Information Modeling (BIM), Computer-Aided Design (CAD), etc.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote Sensing and LiDAR Applications · 3D Surveying and Cultural Heritage
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Merchant Marine College, Shanghai Maritime University, Shanghai 201306, China
College of Transport & Communications, Shanghai Maritime University, Shanghai 201306, China
College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China
Funding
Open Project Program of the State Key Lab of CAD\&CG (Zhejiang University) under Grant · Hubei Key Laboratory of Inland Shipping Technology under Grant
References (46)
Show source-provided references
1. Huang, J., Stoter, J., Peters, R., and Nan, L. (2022). City3D: Large-Scale Building Reconstruction from Airborne LIDAR Point Clouds. Remote Sens., 14.10.3390/rs14092254 ↗
2. Barnes, D., Gadd, M., Murcutt, P., Newman, P., and Posner, I. (2019). The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset. arXiv.10.1109/ICRA40945.2020.9196884 ↗
3. RANSAC-based Multi Primitive Building Reconstruction from 3D Point Clouds10.1016/j.isprsjprs.2021.12.012 ↗
4. Sun, C., Miao, L., Wang, M., Shi, J., and Ding, J. (2023). Research on Point Cloud Hole Filling and 3D Reconstruction in Reflective Area. Sci. Rep., 13.10.1038/s41598-023-45648-5 ↗
5. Applications of Machine Learning to BIM: A Systematic Literature Review10.1016/j.aei.2021.101474 ↗
6. Deep Learning Based Approaches from Semantic Point Clouds to Semantic BIM Models for Heritage Digital Twin10.1186/s40494-024-01179-4 ↗
7. Triplane generator-based NeRF-GAN framework for single-view ship reconstruction10.1080/17538947.2025.2496406 ↗
8. Wind resistance aerial path planning for efficient reconstruction of offshore ship10.1080/17538947.2022.2140852 ↗
9. Research on Building Contour Extraction and Regularization Algorithm Based on LIDAR Data
10. LIDAR Data Reduction Assisted by Optical Image for 3D Building Reconstruction10.1016/j.ijleo.2014.08.016 ↗
11. Point2Roof: End-to-end 3D Building Roof Modeling from Airborne LIDAR Point Clouds10.1016/j.isprsjprs.2022.08.027 ↗
12. Bourki, A., de La Gorce, M., Marlet, R., and Komodakis, N. (2017, January 24–31). Patchwork Stereo: Scalable, Structure-Aware 3D Reconstruction in Man-Made Environments. Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA, USA.10.1109/WACV.2017.39 ↗
13. Lan, Z., Yew, Z.J., and Lee, G.H. (2019, January 15–20). Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00992 ↗
14. Nan, L., and Wonka, P. (2017, January 22–29). Polyfit: Polygonal Surface Reconstruction from Point Clouds. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.258 ↗
15. A Search-Classify Approach for Cluttered Indoor Scene Understanding10.1145/2366145.2366156 ↗
16. An Interactive Approach to Semantic Modeling of Indoor Scenes with an RGBD Camera10.1145/2366145.2366155 ↗
17. Lod Generation for Urban Scenes10.1145/2732527 ↗
18. Photo-Inspired Model-Driven 3D Object Modeling
19. Structure Recovery by Part Assembly10.1145/2366145.2366199 ↗
20. Sagnet: Structure-Aware Generative Network for 3D-Shape Modeling
21. Dai, A., and Nießner, M. (2019, January 15–20). Scan2mesh: From Unstructured Range Scans to 3D Meshes. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00572 ↗
22. Erler, P., Guerrero, P., Ohrhallinger, S., Mitra, N.J., and Wimmer, M. (2020, January 23–28). Points2surf Learning Implicit Surfaces From Point Clouds. Proceedings of the 2020 European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58558-7_7 ↗
23. Sun, J., Chen, X., Wang, Q., Li, Z., Averbuch-Elor, H., Zhou, X., and Snavely, N. (2022, January 7–11). Neural 3D Reconstruction in the Wild. Proceedings of the ACM SIGGRAPH 2022 Conference Proceedings, Vancouver, BC, Canada.10.1145/3528233.3530718 ↗
24. RAPter: Rebuilding Man-Made Scenes with Regular Arrangements of Planes10.1145/2766995 ↗
25. A Survey of Urban Reconstruction10.1111/cgf.12077 ↗
26. Non-Local Scan Consolidation for 3D Urban Scenes10.1145/1778765.1778831 ↗
27. Smartboxes for Interactive Urban Reconstruction10.1145/1778765.1778830 ↗
28. Li, Y., Zheng, Q., Sharf, A., Cohen-Or, D., Chen, B., and Mitra, N.J. (2011, January 6–13). 2D-3D Fusion for Layer Decomposition of Urban Facades. Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain.10.1109/ICCV.2011.6126329 ↗
29. O-Snap: Optimization-Based Snapping for Modeling Architecture10.1145/2421636.2421642 ↗
30. Surface Reconstruction Through Point Set Structuring10.1111/cgf.12042 ↗
31. Semantic Decomposition and Reconstruction of Residential Scenes from LIDAR Data10.1145/2461912.2461969 ↗
32. Li, M., Wonka, P., and Nan, L. (2016, January 11–14). Manhattan-World Urban Reconstruction from Point Clouds. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46493-0_4 ↗
33. Large-Scale Urban Point Cloud Labeling and Reconstruction10.1016/j.isprsjprs.2018.02.008 ↗
34. Modelling of Buildings from Aerial LIDAR Point Clouds Using TINs and Label Maps10.1016/j.isprsjprs.2019.06.003 ↗
35. Albano, R. (2019). Investigation on Roof Segmentation for 3D Building Reconstruction from Aerial LIDAR Point Clouds. Appl. Sci., 9.10.3390/app9214674 ↗
36. Dong, W., Park, J., Yang, Y., and Kaess, M. (2019, January 3–8). GPU Accelerated Robust Scene Reconstruction. Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, China.10.1109/IROS40897.2019.8967693 ↗
37. LIDAR Point Clouds to 3-D Urban Models: A Review10.1109/JSTARS.2017.2781132 ↗
38. Building Model Reconstruction Based on the Technology of 3D Laser Scanning
39. Rusu, R.B., and Cousins, S.B. (2011, January 9–13). 3D is here: Point Cloud Library (PCL). Proceedings of the 2011 IEEE International Conference on Robotics and Automation, Shanghai, China.10.1109/ICRA.2011.5980567 ↗
40. Feature Extraction and Modeling of Urban Building from Vehicle-Borne Laser Scanning Data
41. Milioto, A., Vizzo, I., Behley, J., and Stachniss, C. (2019, January 3–8). Rangenet++: Fast and accurate LIDAR semantic segmentation. Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, China.10.1109/IROS40897.2019.8967762 ↗
42. A Delaunay-based Region-growing Approach to Surface Reconstruction from Unorganized Points10.1016/j.cad.2004.09.011 ↗
43. Toward Better Boundary Preserved Supervoxel Segmentation for 3D Point Clouds10.1016/j.isprsjprs.2018.05.004 ↗
44. An Approach to 3D Model Fusion in GIS Systems and Its Application in A Future ECDIS10.1016/j.cageo.2016.01.008 ↗
45. Laine, S., and Karras, T. (2011, January 5–7). High-Performance Software Rasterization on GPUs. Proceedings of the ACM SIGGRAPH Symposium on High Performance Graphics, Vancouver, BC, Canada.10.1145/2018323.2018337 ↗
46. Screened poisson surface reconstruction10.1145/2487228.2487237 ↗