GeoT: Geometry-guided Instance-dependent Transition Matrix for Semi-supervised Tooth Point Cloud Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913749921693696 |
|---|---|
| author | Yu, Weihao Guo, Xiaoqing Li, Chenxin Liu, Yifan Yuan, Yixuan |
| author_facet | Yu, Weihao Guo, Xiaoqing Li, Chenxin Liu, Yifan Yuan, Yixuan |
| contents | Achieving meticulous segmentation of tooth point clouds from intra-oral scans stands as an indispensable prerequisite for various orthodontic applications. Given the labor-intensive nature of dental annotation, a significant amount of data remains unlabeled, driving increasing interest in semi-supervised approaches. One primary challenge of existing semi-supervised medical segmentation methods lies in noisy pseudo labels generated for unlabeled data. To address this challenge, we propose GeoT, the first framework that employs instance-dependent transition matrix (IDTM) to explicitly model noise in pseudo labels for semi-supervised dental segmentation. Specifically, to handle the extensive solution space of IDTM arising from tens of thousands of dental points, we introduce tooth geometric priors through two key components: point-level geometric regularization (PLGR) to enhance consistency between point adjacency relationships in 3D and IDTM spaces, and class-level geometric smoothing (CLGS) to leverage the fixed spatial distribution of tooth categories for optimal IDTM estimation. Extensive experiments performed on the public Teeth3DS dataset and private dataset demonstrate that our method can make full utilization of unlabeled data to facilitate segmentation, achieving performance comparable to fully supervised methods with only $20\%$ of the labeled data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16976 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GeoT: Geometry-guided Instance-dependent Transition Matrix for Semi-supervised Tooth Point Cloud Segmentation Yu, Weihao Guo, Xiaoqing Li, Chenxin Liu, Yifan Yuan, Yixuan Computer Vision and Pattern Recognition Artificial Intelligence Achieving meticulous segmentation of tooth point clouds from intra-oral scans stands as an indispensable prerequisite for various orthodontic applications. Given the labor-intensive nature of dental annotation, a significant amount of data remains unlabeled, driving increasing interest in semi-supervised approaches. One primary challenge of existing semi-supervised medical segmentation methods lies in noisy pseudo labels generated for unlabeled data. To address this challenge, we propose GeoT, the first framework that employs instance-dependent transition matrix (IDTM) to explicitly model noise in pseudo labels for semi-supervised dental segmentation. Specifically, to handle the extensive solution space of IDTM arising from tens of thousands of dental points, we introduce tooth geometric priors through two key components: point-level geometric regularization (PLGR) to enhance consistency between point adjacency relationships in 3D and IDTM spaces, and class-level geometric smoothing (CLGS) to leverage the fixed spatial distribution of tooth categories for optimal IDTM estimation. Extensive experiments performed on the public Teeth3DS dataset and private dataset demonstrate that our method can make full utilization of unlabeled data to facilitate segmentation, achieving performance comparable to fully supervised methods with only $20\%$ of the labeled data. |
| title | GeoT: Geometry-guided Instance-dependent Transition Matrix for Semi-supervised Tooth Point Cloud Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.16976 |