Cross-Domain multi-channel transformer for point cloud registration in cultural heritage digital preservation
Source abstract
Abstract
Point cloud registration plays a crucial role in preservation and digitization of cultural heritage by accurately aligning multiple point cloud datasets to create a complete 3D model. However, the complexity and diversity of objects lead to low-overlap and significant variations, posing challenges in achieving high accuracy, robustness and generalizability. This study proposes a Cross-Domain Multi-Channel Transformer (CDMCT) to address these challenges. The multi-channel dynamic encoding to enhance model’s sensitivity to local structures and angular relationships. The cross-domain convergence network preserves the global relationships within point cloud and the overall structural information. The integration of graph networks allows for flexible handling of local feature variations. We trained on 3DMatch and KITTI, and validated on cultural heritage datasets Terracotta Warriors and WHU-TLS ancient buildings. Experimental results show that CDMCT achieves significant improvements in registration accuracy and robustness, demonstrating its broad application potential in the digital preservation of cultural heritage.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: 3D Surveying and Cultural Heritage · Image Processing and 3D Reconstruction · 3D Shape Modeling and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (44)
Show source-provided references
1. Wang, M., Chen, G., Yang, Y., Yuan, L. & Yue, Y. Point tree transformer for point cloud registration. IEEE Trans. Circuit. Syst. Video Technol. 35, 6756–6772 (2025).10.1109/TCSVT.2025.3526680 ↗
2. Fu, S. et al. Modified lshade-spacma with new mutation strategy and external archive mechanism for numerical optimization and point cloud registration. Artif. Intel. Rev. 58, 72 (2025).10.1007/s10462-024-11053-1 ↗
3. Markiewicz, J., Kot, P., Markiewicz, Ł. & Muradov, M. The evaluation of hand-crafted and learned-based features in terrestrial laser scanning-structure-from-motion (tls-sfm) indoor point cloud registration: the case study of cultural heritage objects and public interiors. Heritage Sci. 11, 254 (2023).10.1186/s40494-023-01099-9 ↗
4. Liu, S., Mohd Jaki, B. M., Huang, Y., Dong, M. & Liu, Q. Multiscale hierarchy denoising method for heritage building point cloud model noise removal. NPJ Heritage Sci. 13, 199 (2025).10.1038/s40494-025-01639-5 ↗
5. Chen, J. et al. High precision 3d reconstruction and target location based on the fusion of visual features and point cloud registration. Measurement 243, 116455 (2025).10.1016/j.measurement.2024.116455 ↗
6. Wu, P. et al. Spiking point transformer for point cloud classification. Artif. Intel. 39, 21563–21571 (2025).10.1609/aaai.v39i20.35459 ↗
7. Yan, X. et al. Adversenet: A unified lidar point cloud denoising network for autonomous driving in adverse weather. IEEE Sensors J. 25, 8950–8961 (2025).10.1109/JSEN.2024.3505234 ↗
8. Han, R. et al. Neupan: Direct point robot navigation with end-to-end model-based learning. IEEE Trans. Robot. 41, 2804–2824 (2025).10.1109/TRO.2025.3554252 ↗
9. Wang, Y., Zhou, P., Geng, G., An, L. & Zhou, M. Enhancing point cloud registration with transformer: cultural heritage protection of the terracotta warriors. Heritage Sci. 12, 314 (2024).10.1186/s40494-024-01425-9 ↗
10. Yue, Y. et al. Edgeregnet: Edge feature-based multimodal registration network between images and lidar point clouds. arXiv https://doi.org/10.48550/arXiv.2503.15284 (2025).10.48550/arXiv.2503.15284 ↗
11. Leahy, J., Jabari, S., Lichti, D. & Salehitangrizi, A. Enhancing cross-modal camera image and lidar data registration using feature-based matching. Remote Sens. 17, 357 (2025).10.3390/rs17030357 ↗
12. Hu, Y., Li, B., Xu, C., Saydam, S. & Zhang, W. Featsync: 3d point cloud multiview registration with attention feature-based refinement. Neurocomputing 600, 128088 (2024).10.1016/j.neucom.2024.128088 ↗
13. Li, M., Liu, H., Xie, F. & Huang, H. Point cloud-based end-to-end formation control using a two stage sac algorithm. IEEE Robot. Autom. Lett. 10, 2319–2326 (2025).10.1109/LRA.2025.3530161 ↗
14. Jiang, L., Liu, Y., Dong, Z., Li, Y. & Lin, Y. Lightweight deep learning method for end-to-end point cloud registration. Graphical Models 137, 101252 (2025).10.1016/j.gmod.2024.101252 ↗
15. Huang, X. et al. Unsupervised point cloud registration by learning unified gaussian mixture models. IEEE Robot. Autom. Lett. 7, 7028–7035 (2022).10.1109/LRA.2022.3180443 ↗
16. Wang, H. et al. Robust multiview point cloud registration with reliable pose graph initialization and history reweighting. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9506–9515 (IEEE, 2023).10.1109/CVPR52729.2023.00917 ↗
17. Kim, J., Kim, J., Paik, S. & Kim, H. Point cloud registration considering safety nets during scaffold installation using sensor fusion and deep learning. Autom. Construct. 159, 105277 (2024).10.1016/j.autcon.2024.105277 ↗
18. Choy, C., Park, J. & Koltun, V. Fully convolutional geometric features. In Proc. IEEE/CVF international conference on computer vision, 8958–8966 (IEEE, 2019).10.1109/ICCV.2019.00905 ↗
19. Yuan, M., Huang, X., Fu, K., Li, Z. & Wang, M. Boosting 3d point cloud registration by transferring multi-modality knowledge. In 2023 IEEE International Conference on Robotics and Automation (ICRA), 11734–11741 (IEEE, 2023).10.1109/ICRA48891.2023.10161411 ↗
20. Yuan, M. et al. Robust point cloud registration via random network co-ensemble. IEEE Trans. Circuits Syst. Video Technol. 34, 5742–5752 (2024).10.1109/TCSVT.2024.3364175 ↗
21. Wu, X. et al. Point transformer v3: Simpler faster stronger. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 4840–4851 (IEEE, 2024).10.1109/CVPR52733.2024.00463 ↗
22. Chen, Z. et al. Vision transformer adapter for dense predictions. arXiv https://doi.org/10.48550/arXiv.2205.08534 (2023).10.48550/arXiv.2205.08534 ↗
23. Lu, Y. et al. Transflow: Transformer as flow learner. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 18063–18073 (IEEE/CVF, 2023).10.1109/CVPR52729.2023.01732 ↗
24. Yew, Z. J. & Lee, G. H. Regtr: End-to-end point cloud correspondences with transformers. arXiv https://doi.org/10.48550/arXiv.2205.08534 (2022).10.48550/arXiv.2205.08534 ↗
25. Yuan, Y. et al. Egst: Enhanced geometric structure transformer for point cloud registration. IEEE Transactions on Visualization and Computer Graphics, 6222−6234 (2023).10.1109/TVCG.2023.3329578 ↗
26. Yu, H. et al. Riga: Rotation-invariant and globally-aware descriptors for point cloud registration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 3796−3812 (IEEE, 2024).10.1109/TPAMI.2023.3349199 ↗
27. Zeng, A. et al. 3dmatch: Learning local geometric descriptors from rgb-d reconstructions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 199−208 (IEEE, 2017).10.1109/CVPR.2017.29 ↗
28. Geiger, A., Lenz, P. & Urtasun, R. Are we ready for autonomous driving? the kitti vision benchmark suite. In 2012 IEEE Conference on Computer Vision and Pattern Recognition, 3354−3361 (IEEE, 2012).10.1109/CVPR.2012.6248074 ↗
29. Yang, B., Han, X. & Dong, Z. Point cloud benchmark dataset whu-tls and whu-mls for deep learning. J. Remote Sens 25, 231–240 (2021).
30. Bai, X. et al. D3feat: Joint learning of dense detection and description of 3d local features. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 6359–6367 (2020).10.1109/CVPR42600.2020.00639 ↗
31. Huang, S., Gojcic, Z., Usvyatsov, M., Wieser, A. & Schindler, K. Predator: Registration of 3d point clouds with low overlap. In Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition, 4267–4276 (2021).10.1109/CVPR46437.2021.00425 ↗
32. Fischler, M. A. & Bolles, R. C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24, 381–395 (1981).10.1145/358669.358692 ↗
33. Thomas, H. et al. Kpconv: Flexible and deformable convolution for point clouds. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 6411–6420 (IEEE, 2019).10.1109/ICCV.2019.00651 ↗
34. Pan, L., Cai, Z. & Liu, Z. Robust partial-to-partial point cloud registration in a full range. IEEE Robot. Autom. Lett. 9, 2861–2868 (2024).10.1109/LRA.2024.3360858 ↗
35. Xu, H., Liu, S., Wang, G., Liu, G. & Zeng, B. Omnet: Learning overlapping mask for partial-to-partial point cloud registration. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 3132–3141 (IEEE, 2021).10.1109/ICCV48922.2021.00312 ↗
36. Qin, Z. et al. Geometric transformer for fast and robust point cloud registration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 11143–11152 (IEEE/CVF, 2022).10.1109/CVPR52688.2022.01086 ↗
37. Wang, H. et al. Roreg: Pairwise point cloud registration with oriented descriptors and local rotations. IEEE Trans. Pattern Anal. Mach. Intell. 45, 10376–10393 (2023).10.1109/TPAMI.2023.3244951 ↗
38. Mei, G. et al. Unsupervised deep probabilistic approach for partial point cloud registration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13611–13620 (IEEE, 2023).10.1109/CVPR52729.2023.01308 ↗
39. Zhang, X., Yang, J., Zhang, S. & Zhang, Y. 3d registration with maximal cliques. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 17745–17754 (IEEE, 2023).10.1109/CVPR52729.2023.01702 ↗
40. Ao, S., Hu, Q., Yang, B., Markham, A. & Guo, Y. Spinnet: Learning a general surface descriptor for 3d point cloud registration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 11753–11762 (IEEE, 2021).10.1109/CVPR46437.2021.01158 ↗
41. Lu, F. et al. Hregnet: A hierarchical network for large-scale outdoor lidar point cloud registration. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 16014–16023 (IEEE, 2021).10.1109/ICCV48922.2021.01571 ↗
42. Zhang, Z. et al. End-to-end learning the partial permutation matrix for robust 3d point cloud registration. In Proceedings of the AAAI Conference on Artificial Intelligence, 3399–3407 (AAAI, 2022).10.1609/aaai.v36i3.20250 ↗
43. Poiesi, F. & Boscaini, D. Learning general and distinctive 3d local deep descriptors for point cloud registration. IEEE Trans. Pattern Anal. Mach. Intell. 45, 3979–3985 (2022).
44. Chen, Z., Sun, K., Yang, F., Guo, L. & Tao, W. Sc2-pcr++: Rethinking the generation and selection for efficient and robust point cloud registration. IEEE Trans. Pattern Anal. Mach. Intell. 45, 12358–12376 (2023).10.1109/TPAMI.2023.3272557 ↗