Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.16620 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917350164398080 |
|---|---|
| author | He, Qiang Qu, Wentian Dai, Jiajia Lei, Changsong Wang, Shaofeng Zuo, Feifei Wang, Yajie Liang, Yaqian Deng, Xiaoming Ma, Cuixia Liu, Yong-Jin Wang, Hongan |
| author_facet | He, Qiang Qu, Wentian Dai, Jiajia Lei, Changsong Wang, Shaofeng Zuo, Feifei Wang, Yajie Liang, Yaqian Deng, Xiaoming Ma, Cuixia Liu, Yong-Jin Wang, Hongan |
| contents | Accurate semantic segmentation of 3D dental models is essential for digital dentistry applications such as orthodontics and dental implants. However, due to complex tooth arrangements and similarities in shape among adjacent teeth, existing methods struggle with accurate segmentation, because they often focus on local geometry while neglecting global contextual information. To address this, we propose TCATSeg, a novel framework that combines local geometric features with global semantic context. We introduce a set of sparse yet physically meaningful superpoints to capture global semantic relationships and enhance segmentation accuracy. Additionally, we present a new dataset of 400 dental models, including pre-orthodontic samples, to evaluate the generalization of our method. Extensive experiments demonstrate that TCATSeg outperforms state-of-the-art approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16620 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TCATSeg: A Tooth Center-Wise Attention Network for 3D Dental Model Semantic Segmentation He, Qiang Qu, Wentian Dai, Jiajia Lei, Changsong Wang, Shaofeng Zuo, Feifei Wang, Yajie Liang, Yaqian Deng, Xiaoming Ma, Cuixia Liu, Yong-Jin Wang, Hongan Computer Vision and Pattern Recognition Accurate semantic segmentation of 3D dental models is essential for digital dentistry applications such as orthodontics and dental implants. However, due to complex tooth arrangements and similarities in shape among adjacent teeth, existing methods struggle with accurate segmentation, because they often focus on local geometry while neglecting global contextual information. To address this, we propose TCATSeg, a novel framework that combines local geometric features with global semantic context. We introduce a set of sparse yet physically meaningful superpoints to capture global semantic relationships and enhance segmentation accuracy. Additionally, we present a new dataset of 400 dental models, including pre-orthodontic samples, to evaluate the generalization of our method. Extensive experiments demonstrate that TCATSeg outperforms state-of-the-art approaches. |
| title | TCATSeg: A Tooth Center-Wise Attention Network for 3D Dental Model Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.16620 |