DiffusionNet++: A Robust Framework for High-Resolution 3D Dental Mesh Segmentation
Source abstract
Abstract
Accurate segmentation of 3D dental structures is essential for oral diagnosis, orthodontic planning, and digital dentistry. With the rapid advancement of 3D scanning and modeling technologies, high-resolution dental data have become increasingly common. However, existing approaches still struggle to process such high-resolution data efficiently. Current models often suffer from excessive parameter counts, slow inference, high computational overhead, and substantial GPU memory usage. These limitations compel many studies to downsample the input data to reduce training and inference costs—an operation that inevitably diminishes critical geometric details, blurs tooth boundaries, and compromises both fine-grained structural accuracy and model robustness. To address these challenges, this study proposes DiffusionNet++, an end-to-end segmentation framework capable of operating directly on raw high-resolution dental data. Building upon the standard DiffusionNet architecture, our method introduces a normal-enhanced multi-feature input strategy together with a lightweight SE channel-attention mechanism, enabling the model to effectively exploit local directional cues, curvature variations, and other higher-order geometric attributes while adaptively emphasizing discriminative feature channels. Experimental results demonstrate that the coordinates + normal feature configuration consistently delivers the best performance. DiffusionNet++ achieves substantial improvements in overall accuracy (OA), mean Intersection over Union (mIoU), and individual class IoU across all data types, while maintaining strong robustness and generalization on challenging cases, such as missing teeth and partially scanned data. Qualitative visualizations further corroborate these findings, showing superior boundary consistency, finer structural preservation, and enhanced recovery of incomplete regions. Overall, DiffusionNet++ offers an efficient, stable, and highly accurate solution for high-resolution 3D tooth segmentation, providing a powerful foundation for automated digital dentistry research and real-world clinical applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Dental Radiography and Imaging · Advanced Neural Network Applications · Dental Research and COVID-19
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer Science and Technology, Qingdao University, Qingdao 266071, China
References (38)
Show source-provided references
1. Three-dimensional visualisation of the fetal heart using prenatal MRI with motion-corrected slice-volume registration: A prospective, single-centre cohort study10.1016/S0140-6736(18)32490-5 ↗
2. Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography10.1038/s41598-020-76282-0 ↗
3. Efficient high-resolution deep learning: A survey10.1145/3645107 ↗
4. DiffusionNet: Discretization agnostic learning on surfaces
5. Maturana, D., and Scherer, S. (October, January 28). VoxNet: A 3D convolutional neural network for real-time object recognition. Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany.10.1109/IROS.2015.7353481 ↗
6. Hu, Z., Bai, X., Shang, J., Zhang, R., Dong, J., Wang, X., Sun, G., Fu, H., and Tai, C.-L. (2021, January 11–17). VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.01520 ↗
7. Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E. (2015, January 7–13). Multi-view convolutional neural networks for 3D shape recognition. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.114 ↗
8. Feng, Y., Zhang, Z., Zhao, X., Ji, R., and Gao, Y. (2018, January 18–23). GV-CNN: Group-view convolutional neural networks for 3D shape recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00035 ↗
9. Kundu, A., Yin, X., Fathi, A., Ross, D., Brewington, B., Funkhouser, T., and Pantofaru, C. (2020, January 23–28). Virtual multi-view fusion for 3D semantic segmentation. Proceedings of the Computer Vision—ECCV 2020: 16th European Conference, Glasgow, UK.10.1007/978-3-030-58586-0_31 ↗
10. Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017, January 21–26). PointNet: Deep learning on point sets for 3D classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.
11. Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017, January 4–9). PointNet++: Deep hierarchical feature learning on point sets in a metric space. Proceedings of the NIPS’17: Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA.
12. Context-aware 3D point cloud semantic segmentation with plane guidance10.1109/TMM.2022.3212914 ↗
13. Feng, Y., Feng, Y., You, H., Zhao, X., and Gao, Y. (February, January 27). MeshNet: Mesh neural network for 3D shape representation. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
14. Singh, V.V., Sheshappanavar, S.V., and Kambhamettu, C. (2021, January 20–24). MeshNet++: A Network with a Face. Proceedings of the ACM Multimedia, Virtual.10.1145/3474085.3475468 ↗
15. MeshWalker: Deep mesh understanding by random walks10.1145/3414685.3417806 ↗
16. MeshCNN: A network with an edge
17. White spot lesions in orthodontics: Prevention and treatment. A descriptive review
18. Cui, Z., Li, C., and Wang, W. (2019, January 15–20). ToothNet: Automatic tooth instance segmentation and identification from cone beam CT images. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00653 ↗
19. Weighted Sparse Convolution and Transformer Feature Aggregation Networks for 3D Dental Segmentation10.1109/ACCESS.2024.3462521 ↗
20. Automatic 3D tooth segmentation using convolutional neural networks in harmonic parameter space10.1016/j.gmod.2020.101071 ↗
21. Yu, M., Guo, Y., Sun, D., Pei, Y., and Xu, T. (2020, January 16–18). Automatic tooth segmentation and 3D reconstruction from panoramic and lateral radiographs. Proceedings of the Pattern Recognition and Computer Vision: Third Chinese Conference, PRCV 2020, Nanjing, China.10.1007/978-3-030-60633-6_5 ↗
22. TSegLab: Multi-stage 3D dental scan segmentation and labeling10.1016/j.compbiomed.2024.109535 ↗
23. Kim, T., Cho, Y., Kim, D., Chang, M., and Kim, Y.-J. (2020). Tooth segmentation of 3D scan data using generative adversarial networks. Appl. Sci., 10.10.3390/app10020490 ↗
24. A fully automated method for 3D individual tooth identification and segmentation in dental CBCT10.1109/TPAMI.2021.3086072 ↗
25. Accuracy and efficiency of automatic tooth segmentation in digital dental models using deep learning10.1038/s41598-022-13595-2 ↗
26. Zanjani, F.G., Moin, D.A., Claessen, F., Cherici, T., Parinussa, S., Pourtaherian, A., Zinger, S., and de With, P.H.N. (2019). Mask-MCNet: Instance Segmentation in 3D Point Cloud of Intra-oral Scans. Medical Image Computing and Computer Assisted Intervention—MICCAI 2019, Springer International Publishing.10.1007/978-3-030-32254-0_15 ↗
27. TSegNet: An efficient and accurate tooth segmentation network on 3D dental model10.1016/j.media.2020.101949 ↗
28. Qiu, L., Ye, C., Chen, P., Liu, Y., Han, X., and Cui, S. (2022, January 19–24). Darch: Dental arch prior-assisted 3D tooth instance segmentation with weak annotations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.02009 ↗
29. Deep multi-scale mesh feature learning for automated labeling of raw dental surfaces from 3D intraoral scanners10.1109/TMI.2020.2971730 ↗
30. Two-stage mesh deep learning for automated tooth segmentation and landmark localization on 3D intraoral scans10.1109/TMI.2022.3180343 ↗
31. Two-stream graph convolutional network for intra-oral scanner image segmentation10.1109/TMI.2021.3124217 ↗
32. THISNet: Tooth Instance Segmentation on 3D Dental Models via Highlighting Tooth Regions10.1109/TCSVT.2023.3341805 ↗
33. TeethGNN: Semantic 3D Teeth Segmentation With Graph Neural Networks10.1109/TVCG.2022.3153501 ↗
34. DilatedToothSegNet: Tooth Segmentation Network on 3D Dental Meshes Through Increasing Receptive Vision10.1007/s10278-024-01061-6 ↗
35. Atwood, J., and Towsley, D. (2016, January 5–10). Diffusion-convolutional neural networks. Proceedings of the NIPS’16: Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain.
36. Enhancing 3D U-Net with Residual and Squeeze-and-Excitation Attention Mechanisms for Improved Brain Tumor Segmentation in Multimodal MRI
37. Glorot, X., Bordes, A., and Bengio, Y. (2011). Deep Sparse Rectifier Neural Networks. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2011), JMLR Workshop and Conference Proceedings.
38. Ben-Hamadou, A., Smaoui, O., Chaabouni-Chouayakh, H., Rekik, A., Pujades, S., Boyer, E., Strippoli, J., Thollot, A., Setbon, H., and Trosset, C. (2022). Teeth3ds: A benchmark for teeth segmentation and labeling from intra-oral 3D scans. arXiv.