Multi-scale geometric variations semantic segmentation in Chinese architecture point clouds
Source abstract
Abstract
Point cloud semantic segmentation plays a crucial role in the information modeling of traditional Chinese architecture. The complex structures of traditional Chinese buildings, along with rare-class components and large size variations of their characteristic elements, pose considerable challenges for automated semantic segmentation. To address these challenges, we present UNet-PADRB, an enhanced residual U-Net architecture that integrates Dynamic Graph Convolutional Neural Networks (DGCNN) block within a novel Position-Aware Dilated Residual Block (PADRB) framework for simultaneous local and global feature extraction. Specifically, U-Net processes the hierarchical characteristics of rare-class components, while PADRB combines residual learning and position-sensitive graph convolution to handle spatial topology of large size variations features. Experiments on Zhangguying Village point clouds show state-of-the-art performance (OA: 91.89%, mIoU: 71.07%), with significant improvements for small rare-class elements (e.g., doors: +32.7%) and large composite structures (e.g., courtyards: +18.57%). This advances heritage documentation for virtual restoration and risk management.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: 3D Surveying and Cultural Heritage · 3D Shape Modeling and Analysis · Remote Sensing and LiDAR Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (52)
Show source-provided references
1. Liu, C., Cao, Y., Yang, C., Zhou, Y. & Ai, M. Pattern identification and analysis for the traditional village using low altitude UAV-borne remote sensing: multifeatured geospatial data to support rural landscape investigation, documentation and management. J. Cult. Herit. 44, 185–195 (2020).10.1016/j.culher.2019.12.013 ↗
2. Vavulin, M. V., Chugunov, K. V., Zaitceva, O. V., Vodyasov, E. V. & Pushkarev, A. A. UAV-based photogrammetry: Assessing the application potential and effectiveness for archaeological monitoring and surveying in the research on the ‘Valley of the Kings’ (Tuva, Russia). Digit. Appl. Archaeol. Cult. Herit. 20, e001722021 (2021).
3. Chiabrando, F., Sammartano, G. & Spanò, A. Historical buildings models and their handling via 3D survey: from points clouds to user-oriented HBIM. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. XLI-B5, 633–640 (2016).10.5194/isprs-archives-XLI-B5-633-2016 ↗
4. McCarthy, J. Multi-image photogrammetry as a practical tool for cultural heritage survey and community engagement. J. Archaeol. Sci. 43, 175–185 (2014).10.1016/j.jas.2014.01.010 ↗
5. Grilli, E., Menna, F. & Remondino, F. A review of point clouds segmentation and classification algorithms. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. XLII-2/W3, 339–344 (2017).10.5194/isprs-archives-XLII-2-W3-339-2017 ↗
6. Grilli, E. & Remondino, F. Classification of 3D Digital Heritage. J. Remote Sens. 11, 847–23 (2019).10.3390/rs11070847 ↗
7. Xie, Y., Tian, J. & Zhu, X. X. Linking Points With Labels in 3D: A Review of Point Cloud Semantic Segmentation. IEEE Geosci. Remote Sens. Mag. 8, 38–59 (2020).10.1109/MGRS.2019.2937630 ↗
8. Yang, S., Hou, M. & Li, S. Three-Dimensional Point Cloud Semantic Segmentation for Cultural Heritage: A Comprehensive Review. J. Remote Sens. 15, 548 (2023).10.3390/rs15030548 ↗
9. Rabbania, T., Heuvelb, F. A. V. D. & Vosselmanc, G. Segmentation of point clouds using smoothness constraint. In Proc. ISPRS Commission V Symposium ‘Image Engineering and Vision Metrology’, Vol. 36, 248–253 (ISPRS, 2006).
10. Pérez-Sinticala, C. et al. Evaluation of Primitive Extraction Methods from Point Clouds of Cultural Heritage Buildings. In Proc. 11th International Conference on Structural Analysis of Historical Constructions (SAHC) Vol. 18, 2332–2341 (Springer International Publishing, 2019).10.1007/978-3-319-99441-3_250 ↗
11. Paiva, P. V. V., Cogima, C. K., Dezen-Kempter, E. & Carvalho, M. A. G. Historical Building Point Cloud Segmentation Combining Hierarchical Watershed Transform and Curvature Analysis. Pattern Recognit. Lett. 135, 114–121 (2020).10.1016/j.patrec.2020.04.010 ↗
12. Wani, M. A. & Arabnia, H. R. Parallel Edge-Region-Based Segmentation Algorithm Targeted at Reconfigurable MultiRing Network. J. Supercomput. 25, 43–62 (2003).10.1023/A:1022804606389 ↗
13. Alshawabkeh, Y. Linear feature extraction from point cloud using color information. npj Herit. Sci. 8, 28 (2020).10.1186/s40494-020-00371-6 ↗
14. Lerma, J. & Biosca, J. Segmentation and filtering of laser scanner data for cultural heritage. In Proc. CIPA 2005 XX International Symposium, Vol. 26, 6–11 (ISPRS, 2005).
15. Spina, S., Debattista, K., Bugeja, K. & Chalmers, A. Point Cloud Segmentation for Cultural Heritage Sites. In Proc. 12th International conference on Virtual Reality, Archaeology and Cultural Heritage, 41–48 (Eurographics Association, 2011).
16. Moyano, J., Nieto, J. A. L., Julián, J. E. N. & Bruno, S. Semantic interpretation of architectural and archaeological geometries: Point cloud segmentation for HBIM parameterisation. Autom. Constr. 130, 103856 (2021).10.1016/j.autcon.2021.103856 ↗
17. Zhang, R., Zhou, X., Zhao, J. & Cao, M. A Semantic Segmentation Algorithm of Ancient Building’s Point Cloud Data. J. Geomat. Inf. Sci. Wuhan. Univ. 45, 753–759 (2020).
18. Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet Classification with Deep Convolutional Neural Networks. NIPS Curran Associates Inc. 25, 1097–1105 (2012).
19. Guo, Y. et al. Deep learning for 3d point clouds: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 43, 4338–4364 (2020).10.1109/TPAMI.2020.3005434 ↗
20. Su, H., Maji, S., Kalogerakis, E. & Learned-Miller, E. Multi-view Convolutional Neural Networks for 3D Shape Recognition. In Proceedings of the IEEE International Conference on Computer Vision(ICCV). 945–953 (IEEE, 2015).10.1109/ICCV.2015.114 ↗
21. Maturana, D. & Scherer, S. VoxNet: A 3D Convolutional Neural Network for Real-Time Object Recognition. In 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 922–928 (IEEE, 2015).10.1109/IROS.2015.7353481 ↗
22. Qi, C. R., Su, H., Mo, K. & Guibas, L. J. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 652–660 (IEEE, 2017).
23. Qi, C. R., Yi, L., Su, H. & Guibas, L. J. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In Proceedings of the 31th on Neural Information Processing Systems (NIPS 2017). 30, 5105–5114 (NIPS, 2017).
24. Malinverni, E. S. et al. Deep learning for semantic segmentation of 3D point cloud. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. XLII-2/W15, 735–742 (2019).10.5194/isprs-archives-XLII-2-W15-735-2019 ↗
25. Qian, G. et al. PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies. In Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS 2022). 35, 23192–23204 (NeurIPS, 2022).
26. Wang, Y. et al. Dynamic Graph CNN for Learning on Point Clouds. Acm Trans. Graph. 38 1–12 (2018).10.1145/3326362 ↗
27. Zhang, K., et al. Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features. In 2021 27th International Conference on Mechatronics and Machine Vision in Practice (M2VIP) (IEEE, 2021).10.1109/M2VIP49856.2021.9665104 ↗
28. Morbidoni, C., Pierdicca, R., Paolanti, M., Quattrini, R. & Mammoli, R. Learning from synthetic point cloud data for historical buildings semantic segmentation. J. Comput. Cult. Herit. 13, 1–18 (2020).10.1145/3409262 ↗
29. Pierdicca, R. et al. Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage. J. Remote Sens. 12, 1005 (2020).10.3390/rs12061005 ↗
30. Zhou, C., Dong, Y., Hou, M., Ji, Y. & Wen, C. MP-DGCNN for the semantic segmentation of Chinese ancient building point clouds. npj Herit. Sci. 12, 249 (2024).10.1186/s40494-024-01289-z ↗
31. Zeng, Z. et al. Small but mighty: Enhancing 3D point clouds semantic segmentation with U-Next framework. Int J. Appl. Earth OBS 136, 104309 (2025).
32. Atzmon, M., Maron, H. & Lipman, Y. Point Convolutional Neural Networks by Extension Operators. ACM Trans. Graph. 37, 71 (2018).10.1145/3197517.3201301 ↗
33. Liu, Z., Hu, H., Cao, Y., Zhang, Z. & Tong, X. A Closer Look at Local Aggregation Operators in Point Cloud Analysis. In Proceedings of the 16th European Conference on Computer Vision (ECCV 2020). 12368, 326–342 (ECCV, 2020).10.1007/978-3-030-58592-1_20 ↗
34. Yin, C., Wang, B., Gan, V. J. L., Wang, M. & Cheng, J. C. P. Automated semantic segmentation of industrial point clouds using ResPointNet. Autom. Constr. 130, 103874 (2021).10.1016/j.autcon.2021.103874 ↗
35. Thomas, H. et al. KPConv: Flexible and Deformable Convolution for Point Clouds. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 6411–6420 (IEEE, 2019).10.1109/ICCV.2019.00651 ↗
36. Hu, Q. et al. RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 11108–11117 (IEEE, 2020).10.1109/CVPR42600.2020.01112 ↗
37. Zhao, H., Jiang, L., Jia, J., Torr, P. & Koltun, V. Point Transformer. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 16259–16268 (IEEE, 2021).10.1109/ICCV48922.2021.01595 ↗
38. Wu, X., Lao, Y., Jiang, L., Liu, X. & Zhao, H. Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. Adv. Neural Inf. Process. Syst. 35, 33330–33342 (2022).
39. Wu, X. et al. Point Transformer V3: Simpler, Faster, Stronger. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 4840–4851 (IEEE, 2024).10.1109/CVPR52733.2024.00463 ↗
40. Yu, X. et al. Point-BERT: Pre-Training 3D Point Cloud Transformers with Masked Point Modeling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 19313–19322 (IEEE, 2022).10.1109/CVPR52688.2022.01871 ↗
41. Lai, X. et al. Stratified Transformer for 3D Point Cloud Segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 8500–8509 (IEEE, 2022).10.1109/CVPR52688.2022.00831 ↗
42. Lu, D., Xu, L., Zhou, J., Gao, K. Y. & Li, J. 3DLST: 3D Learnable Supertoken Transformer for LiDAR Point Cloud Scene Segmentation. Int. J. Appl. Earth Obs. Geoinf. 140, 104572 (2025).
43. Landrieu, L. & Simonovsky, M. Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 4558–4567 (IEEE, 2018).10.1109/CVPR.2018.00479 ↗
44. Robert, D., Raguet, H. & Landrieu, L. Efficient 3D Semantic Segmentation with Superpoint Transformer. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 17195–17204 (IEEE, 2023).10.1109/ICCV51070.2023.01577 ↗
45. Huang, S. et al. Weakly supervised 3D point cloud semantic segmentation for architectural heritage using teacher-guided consistency and contrast learning. Autom. Constr. 168, 105831 (2024).10.1016/j.autcon.2024.105831 ↗
46. Zhang, Z., Wang, T., Wang, X. & Zhan, Z. Weakly Supervised Learning Method for Semantic Segmentation of Large-Scale 3D Point Cloud Based on Transformers. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 48, 887–894 (2024).10.5194/isprs-archives-XLVIII-1-2024-887-2024 ↗
47. Xu, X. & Lee, G. H. Weakly Supervised Semantic Point Cloud Segmentation: Towards 10× Fewer Labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 13706–13715 (IEEE, 2020).10.1109/CVPR42600.2020.01372 ↗
48. Ren, D. et al. MFFNet: multimodal feature fusion network for point cloud semantic segmentation. Vis. Comput 40, 5155–5167 (2024).10.1007/s00371-023-02907-w ↗
49. Poliyapram, V., Wang, W. & Nakamura, R. A Point-Wise LiDAR and Image Multimodal Fusion Network (PMNet) for Aerial Point Cloud 3D Semantic Segmentation. J. Remote Sens. 11, 2961 (2019).10.3390/rs11242961 ↗
50. Chen, R., Wu, J., Luo, Y. & Xu, G. PointMM: Point Cloud Semantic Segmentation CNN under Multi-Spatial Feature Encoding and Multi-Head Attention Pooling. J. Remote Sens. 16, 1246 (2024).10.3390/rs16071246 ↗
51. Feng, S. & Liu, P. Confucianism’s Influence on Spatial Design of the Kindred Settlement and Its Enlightenment:A Case Study of Zhangguying Village,Hunan. Econ. Geogr. 42, 206–214 (2022).
52. Li, B., Zheng, S., Liu, P. & Dou, Y. Pattern Language Of The Spatial Arrangement Of Traditional Villages A Case Study Of Zhangguying Village. Sci. Geogr. Sin. 39, 1691–1701 (2019).