Precise Geometric-Priors-Guided 3D Point Cloud Segmentation Network for Auricle Region: GeoPriors-3DEarSeg
Source abstract
Abstract
This paper addresses the core challenges in the 3D point cloud segmentation of the human auricle region, including the low distinguishability of weak-boundary features, the lack of anatomical priors in existing methods, the tendency of boundary features to be overwhelmed by background noise, and the weakening of supervisory signals. We propose GeoPriors-3DEarSeg, a precise geometric-priors-guided 3D point cloud segmentation network for auricle regions. The network incorporates complementary geometric features from three dimensions, normal vector orientation, local Gaussian curvature, and shape diameter function, to characterize the intrinsic geometric differences at the auricle boundary. A geometric-priors-guided QKV gated attention mechanism is designed to selectively enhance the expression of weak-boundary features. Additionally, we introduce a boundary-aware loss function, NVBLoss, which does not rely on extra annotations to strengthen the supervision of boundary features. The experimental results on a human ear dataset demonstrate that our method achieves a mean intersection over union (mIoU) of 0.9857, outperforms the comparison methods, and precisely segments of weak boundaries in the auricle region. This work provides a technical basis for accurate auricle-region point cloud segmentation and offesr methodological insights for future studies on the weak-boundary segmentation of other medical anatomical structures.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Reconstructive Facial Surgery Techniques · Biometric Identification and Security · Ear Surgery and Otitis Media
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China
Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education, Beijing 100083, China
Key Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China
Funding
Ministry of Agriculture and Rural Affairs · Fundamental Research Funds for the Central Universities · National Natural Science Foundation of China
References (31)
Show source-provided references
1. Rusu, R.B., Blodow, N., and Beetz, M. (2009). Fast point feature histograms (FPFH) for 3D registration. Proceedings of the 2009 IEEE International Conference on Robotics and Automation, IEEE.10.1109/ROBOT.2009.5152473 ↗
2. Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017). Pointnet: Deep learning on point sets for 3D classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.
3. Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in Neural Information Processing Systems 30 (NIPS 2017), NeurIPS.
4. 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. Proceedings of the IEEE/CVF International Conference on Computer Vision, IEEE.10.1109/ICCV.2019.00651 ↗
5. Dynamic convolution for 3D point cloud instance segmentation
6. Zhao, H., Jiang, L., Jia, J., Torr, P.H., and Koltun, V. (2021). Point transformer. Proceedings of the IEEE/CVF International Conference on Computer Vision, IEEE Computer Society.10.1109/ICCV48922.2021.01595 ↗
7. Wu, X., Lao, Y., Jiang, L., Liu, X., and Zhao, H. (2022). Point transformer v2: Grouped vector attention and partition-based pooling. Advances in Neural Information Processing Systems 35 (NeurIPS 2022), NeurIPS.
8. Wu, X., Jiang, L., Wang, P.S., Liu, Z., Liu, X., Qiao, Y., Ouyang, W., He, T., and Zhao, H. (2024). Point transformer v3: Simpler faster stronger. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR52733.2024.00463 ↗
9. Yue, Y., Robert, D., Wang, J., Hong, S., Wegner, J.D., Rupprecht, C., and Schindler, K. (2026). Litept: Lighter yet stronger point transformer. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE.
10. Lai, X., Liu, J., Jiang, L., Wang, L., Zhao, H., Liu, S., Qi, X., and Jia, J. (2022). Stratified transformer for 3D point cloud segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR52688.2022.00831 ↗
11. Swin3d: A pretrained transformer backbone for 3d indoor scene understanding10.26599/CVM.2025.9450383 ↗
12. Guennebaud, G., and Gross, M. (2007). Algebraic point set surfaces. ACM Transactions on Graphics, Association for Computing Machinery. ACM SIGGRAPH 2007 Papers.10.1145/1275808.1276406 ↗
13. Lan, S., Yu, R., Yu, G., and Davis, L.S. (2019). Modeling local geometric structure of 3d point clouds using geo-cnn. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR.2019.00109 ↗
14. Enhancing 3D point cloud learning with geometric-aware dynamic graph convolution and Transformer networks10.1007/s11227-025-08190-x ↗
15. Active Shape Models-Their Training and Application10.1006/cviu.1995.1004 ↗
16. Al Arif, S.M.R., Knapp, K., and Slabaugh, G. (2017). Shape-aware Deep Convolutional Neural Network for Vertebrae Segmentation. International Workshop on Computational Methods and Clinical Applications in Musculoskeletal Imaging, Springer.10.1007/978-3-319-74113-0_2 ↗
17. Wu, Y., and Wei, H. (2026). GENet: A Geometry-Enhanced Network for LiDAR Semantic Segmentation. Sensors, 26.10.3390/s26051460 ↗
18. M-PointNet: A Multi-Layer Embedded Deep Learning Model for 3D Intracranial Aneurysm Classification and Segmentation10.1049/ipr2.70275 ↗
19. Yuan, L., Zuo, W., Zhao, Y., Wang, Y., and Rong, P. (2025). 3D Ear Segmentation Based on Multiscale Point Transformer. Proceedings of the 2025 17th International Conference on Human System Interaction (HSI), IEEE.10.1109/HSI66212.2025.11142379 ↗
20. Automatic segmentation of inner ear on CT-scan using auto-context convolutional neural network10.1038/s41598-021-83955-x ↗
21. Wang, J., Wei, L., Wang, L., Zhou, Q., Zhu, L., and Qin, J. (2021). Boundary-aware Transformers for Skin Lesion Segmentation. arXiv.10.1007/978-3-030-87193-2_20 ↗
22. Edge guided bidirectional iterative network in medical image segmentation
23. Jia, H., Liang, X., Liu, Y., Qin, Z., Liu, K., and Dai, C. (2026). Point Cloud Semantic Segmentation Based on Boundary Awareness and Multi-scale Spatial Descriptors. IEEE Trans. Geosci. Remote Sens., 64.10.1109/TGRS.2026.3684655 ↗
24. Focal Loss for Dense Object Detection
25. Milletari, F., Navab, N., and Ahmadi, S.A. (2016). V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), IEEE.10.1109/3DV.2016.79 ↗
26. Kervadec, H., Bouchtiba, J., Desrosiers, C., Granger, E., Dolz, J., and Ayed, I.B. (2019). Boundary loss for highly unbalanced segmentation. Proceedings of the International Conference on Medical Imaging with Deep Learning, PMLR.
27. Hu, X., Li, F., Samaras, D., and Chen, C. (2019). Topology-preserving deep image segmentation. Advances in Neural Information Processing Systems 32 (NeurIPS 2019), NeurIPS.
28. Dai, H., Pears, N., and Smith, W. (2018). A data-augmented 3d morphable model of the ear. Proceedings of the 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), IEEE.10.1109/FG.2018.00065 ↗
29. World Federation of Acupuncture-Moxibustion Societies (2016). Name and Location of Auricular Acupuncture Points (Standard No. WFAS Standard 002:2013).
30. Domain-adaptive faster R-CNN for non-PPE identification on construction sites from body-worn and general images10.1038/s41598-026-35148-7 ↗
31. Domain adaptation using transformer models for automated detection of exterior cladding materials in street view images10.1038/s41598-025-32524-7 ↗