PcBD: A Novel Point Cloud Processing Flow for Boundary Detecting and De-Noising
Source abstract
Abstract
In target detection tasks equipped with depth sensors, it is crucial to adopt the point cloud pretreatment process, which is directly related to the quality of the obtained three-dimensional model of the target. However, there are few methods that can be combined with common preprocessing methods to quickly process ToF camera output. In real-life experiments, the common method is to adopt multiple types of preprocessing methods and adjust parameters separately. We proposed PcBD, a method that integrates outlier removal, boundary detection, and smooth sliders. PcBD does not limit the number of input points, and can remove outliers and predict smooth projection boundaries at one time while ensuring that the total number of points remains unchanged. We also introduced Bound57, a benchmark dataset that contains point clouds with synthetic noise, outliers, and projected boundary labels. Experimental results show that PcBD performs significantly better than state-of-the-art methods in various de-noising and boundary detection tasks.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: 3D Shape Modeling and Analysis · Computer Graphics and Visualization Techniques · Remote Sensing and LiDAR Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of Modern Optical Instrumentation, Zhejiang University, No. 38 Zheda Road, Hangzhou 310027, China
Jiaxing Research Institute, Zhejiang University, Jiaxing 314031, China
Shanghai Institute for Advanced Study of Zhejiang University, Shanghai 201203, China
Funding
“Pioneer” and “Leading Goose” R&D Program of Zhejiang · Key Research and Development Program of JiaXing
References (63)
Show source-provided references
1. RGB-D Mapping: Using Kinect-Style Depth Cameras for Dense 3D Modeling of Indoor Environments10.1177/0278364911434148 ↗
2. Han, D. (2023, January 17–19). Research on Control System Design of Automobile Wind Tunnel Model Test. Proceedings of the 2023 Asia-Europe Conference on Electronics, Data Processing and Informatics (ACEDPI), Prague, Czech Republic.10.1109/ACEDPI58926.2023.00009 ↗
3. Inman, J.A., and Danehy, P.M. (2020, January 22–26). From Wind Tunnels to Flight Vehicles: Visualization and quantitative measurements supporting NASA’s space program. Proceedings of the Optical Sensors and Sensing Congress, Washington, DC, USA.10.1364/LACSEA.2020.LW4E.1 ↗
4. Tanner, C.L., Clark, I.G., and Chen, A. (2018, January 3–10). Overview of the Mars 2020 parachute risk reduction activity. Proceedings of the 2018 IEEE Aerospace Conference, Big Sky, MT, USA.10.1109/AERO.2018.8396717 ↗
5. O’Farrell, C., Muppidi, S., Brock, J.M., Van Norman, J.W., and Clark, I.G. (2017, January 4–11). Development of models for disk-gap-band parachutes deployed supersonically in the wake of a slender body. Proceedings of the 2017 IEEE Aerospace Conference, Big Sky, MT, USA.10.1109/AERO.2017.7943786 ↗
6. SHOT: Unique signatures of histograms for surface and texture description10.1016/j.cviu.2014.04.011 ↗
7. Zhao, H., Jiang, L., Jia, J., Torr, P., and Koltun, V. (2021, January 11–17). Point Transformer. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada.10.1109/ICCV48922.2021.01595 ↗
8. Wang, W., You, X., Chen, L., Tian, J., Tang, F., and Zhang, L. (2022). A Scalable and Accurate De-Snowing Algorithm for LiDAR Point Clouds in Winter. Remote Sens., 14.10.3390/rs14061468 ↗
9. Kurup, A., and Bos, J. (2021). DSOR: A Scalable Statistical Filter for Removing Falling Snow from LiDAR Point Clouds in Severe Winter Weather. arXiv.
10. The Bilateral Filter for Point Clouds10.5201/ipol.2017.179 ↗
11. Si, H., Wei, Z., Zhu, Z., Chen, H., Liang, D., Wang, W., and Wei, M. (2022). LBF:Learnable Bilateral Filter For Point Cloud Denoising. arXiv.
12. Edge-aware point set resampling
13. Zeng, J., Cheung, G., Ng, M., Pang, J., and Yang, C. (2019). 3D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Model. arXiv.10.1109/TIP.2019.2961429 ↗
14. Feature Graph Learning for 3D Point Cloud Denoising10.1109/TSP.2020.2978617 ↗
15. Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017). PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. arXiv.
16. Xu, M., Ding, R., Zhao, H., and Qi, X. (2021). PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds. arXiv.10.1109/CVPR46437.2021.00319 ↗
17. Ao, S., Hu, Q., Yang, B., Markham, A., and Guo, Y. (2021). SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration. arXiv.10.1109/CVPR46437.2021.01158 ↗
18. Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., and Guibas, L.J. (2019). KPConv: Flexible and Deformable Convolution for Point Clouds. arXiv.10.1109/ICCV.2019.00651 ↗
19. 4DenoiseNet: Adverse Weather Denoising from Adjacent Point Clouds10.1109/LRA.2022.3227863 ↗
20. CNN-based Lidar Point Cloud De-Noising in Adverse Weather10.1109/LRA.2020.2972865 ↗
21. Zhao, X., Wen, C., Wang, Y., Bai, H., and Dou, W. (2024). TripleMixer: A 3D Point Cloud Denoising Model for Adverse Weather. arXiv.
22. PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds10.1111/cgf.13753 ↗
23. Duan, C., Chen, S., and Kovacevic, J. (2019). 3D Point Cloud Denoising via Deep Neural Network based Local Surface Estimation. arXiv.10.1109/ICASSP.2019.8682812 ↗
24. Luo, S., and Hu, W. (2020, January 12–16). Differentiable Manifold Reconstruction for Point Cloud Denoising. Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA.10.1145/3394171.3413727 ↗
25. Hermosilla, P., Ritschel, T., and Ropinski, T. (2019). Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning. arXiv.
26. Luo, S., and Hu, W. (2021, January 17). Score-Based Point Cloud Denoising (Learning Gradient Fields for Point Cloud Denoising). Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00454 ↗
27. Estimation of Non-Normalized Statistical Models by Score Matching
28. Vogel, M., Tateno, K., Pollefeys, M., Tombari, F., Rakotosaona, M.J., and Engelmann, F. (2024). P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoising. European Conference on Computer Vision, Springer.10.1007/978-3-031-72627-9_11 ↗
29. A single-stage point cloud cleaning network for outlier removal and denoising10.1016/j.patcog.2023.109366 ↗
30. Li, X., Lu, J., Ding, H., Sun, C., Zhou, J.T., and Meng, C.Y. (2024). Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification. arXiv.10.1609/aaai.v38i19.30129 ↗
31. An Algorithm for Convex Polytopes10.1145/321556.321564 ↗
32. An Efficient Algorithm for Determining the Convex Hull of a Finite Planar Set10.1016/0020-0190(72)90045-2 ↗
33. On the shape of a set of points in the plane10.1109/TIT.1983.1056714 ↗
34. Extraction of Building Roof Boundaries From LiDAR Data Using an Adaptive Alpha-Shape Algorithm10.1109/LGRS.2019.2894098 ↗
35. A non-parametric approach to shape reconstruction from planar point sets through Delaunay filtering10.1016/j.cad.2014.12.002 ↗
36. Yang, Q., Li, Z., Liu, Z., Jiang, X., and Gao, X. (2025). The Circle Pure Rolling Method for Point Cloud Boundary Extraction. Sensors, 25.10.3390/s25010045 ↗
37. Bode, L., Weinmann, M., and Klein, R. (2022). BoundED: Neural Boundary and Edge Detection in 3D Point Clouds via Local Neighborhood Statistics. arXiv.10.1016/j.isprsjprs.2023.09.023 ↗
38. Xiang, P., Wen, X., Liu, Y.S., Cao, Y.P., Wan, P., Zheng, W., and Han, Z. (2021). SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer. arXiv.10.1109/ICCV48922.2021.00545 ↗
39. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. arXiv.
40. Chang, A.X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., and Su, H. (2015). ShapeNet: An Information-Rich 3D Model Repository. arXiv.
41. Fischler, M.A., and Firschein, O. (1987). A Computational Approach to Edge Detection. Readings in Computer Vision, Morgan Kaufmann.
42. The OpenCV Library
43. Yuan, W., Khot, T., Held, D., Mertz, C., and Hebert, M. (2019). PCN: Point Completion Network. arXiv.10.1109/3DV.2018.00088 ↗
44. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
45. Fan, H., Su, H., and Guibas, L.J. (2017, January 21–26). A Point Set Generation Network for 3D Object Reconstruction from a Single Image. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.264 ↗
46. Achlioptas, P., Diamanti, O., Mitliagkas, I., and Guibas, L. (2018, January 10–15). Learning Representations and Generative Models for 3D Point Clouds. Proceedings of the International Conference on Machine Learning (ICML), Stockholm, Sweden.
47. Rusu, R.B., and Cousins, S. (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 ↗
48. Semantic 3D Object Maps for Everyday Manipulation in Human Living Environments10.1007/s13218-010-0059-6 ↗
49. A Density Based Algorithm for Discovering Density Varied Clusters in Large Spatial Databases
50. Mao, A., Yan, B., Ma, Z., and He, Y. (2024, January 16–22). Denoising Point Clouds in Latent Space via Graph Convolution and Invertible Neural Network. Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR52733.2024.00551 ↗
51. Gao, Y., Chen, W., Yu, C., Yao, Y., and Xiao, T. (2017, January 11–13). Automatic extraction of building elevation contours based on LIDAR data. Proceedings of the 2017 4th International Conference on Systems and Informatics (ICSAI), Hangzhou, China.10.1109/ICSAI.2017.8248496 ↗
52. Automatic extraction of boundary characteristic from scatter data
53. Yu, L., Li, X., Fu, C.W., Cohen-Or, D., and Heng, P.A. (2018). EC-Net: An Edge-aware Point set Consolidation Network. arXiv.10.1007/978-3-030-01234-2_24 ↗
54. EdgeFormer: Local patch-based edge detection transformer on point clouds10.1007/s10044-024-01386-6 ↗
55. Learning Part Boundaries from 3D Point Clouds10.1111/cgf.14078 ↗
56. Iterative guidance normal filter for point cloud10.1007/s11042-017-5258-9 ↗
57. Duan, C., Chen, S., and Kovacevic, J. (2018, January 26–28). Weighted multi-projection: 3D point cloud denoising with tangent planes. Proceedings of the 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Anaheim, CA, USA.10.1109/GlobalSIP.2018.8646331 ↗
58. Leal, E., Sanchez-Torres, G., and Branch, J.W. (2020). Sparse Regularization-Based Approach for Point Cloud Denoising and Sharp Features Enhancement. Sensors, 20.10.3390/s20113206 ↗
59. Computing and rendering point set surfaces10.1109/TVCG.2003.1175093 ↗
60. Anisotropic Denoising of 3D Point Clouds by Aggregation of Multiple Surface-Adaptive Estimates10.1109/TVCG.2019.2959761 ↗
61. PCDNF: Revisiting Learning-Based Point Cloud Denoising via Joint Normal Filtering10.1109/TVCG.2023.3292464 ↗
62. Zhang, D., Lu, X., Qin, H., and He, Y. (2020). Pointfilter: Point Cloud Filtering via Encoder-Decoder Modeling. arXiv.10.1109/TVCG.2020.3027069 ↗
63. Registration of large-scale terrestrial laser scanner point clouds: A review and benchmark10.1016/j.isprsjprs.2020.03.013 ↗