Transformer based 3D tooth segmentation via point cloud region partition
You Wu, Hongping Yan, Kun Ding · 2024
Read Transformer based 3D tooth segmentation via point cloud region partition by You Wu, Hongping Yan, Kun Ding (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11574114.txt.
Description
You Wu, Hongping Yan, and Kun Ding present an AI method that labels teeth in 3D dental scans, in a 2024 paper. Accurate labels on point cloud scans aid computer-guided dentistry. Transformer methods capture local detail well. But memory limits stop them from using the whole scene at once.
Their network, PointRegion, splits the cloud into a set of regions first. Each region becomes a compact code. A second module then reads all region codes together to model the global scene. That keeps costs low while still seeing the full mouth. A new step handles the messy, unordered nature of point data. Better tooth maps can support planning for implants, braces, and surgery.
Catalog record
| CREATOR | You Wu, Hongping Yan, Kun Ding |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 87 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |