AI Paper Atlas

Research map / 3D vision / 3D generation

Photo-Guided Tooth Segmentation on 3D Oral Scan Model

Shaojie Zhuang, Guangshun Wei, Jiangxin He, Yuanfeng Zhou

CVPR 2026 · 3D vision › 3D generation · approach: 2D-to-3D pretrained representations

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add an occlusal arch photo via FFG to the geometry-only model (ablation)PMTSeg backbone (PointNet++) · Intraoral scan datasetmIoU: 81.94 -> 92.58Improved
add an occlusal arch photo via FFG (ablation)PMTSeg backbone · Intraoral scan datasetB-IoU: 78.45 -> 86.33Improved
add a frontal photo to the arch photo in FFG (ablation)PMTSeg · Intraoral scan datasetmIoU: 92.58 -> 93.82Improved
add a frontal photo to the arch photo in FFG (ablation)PMTSeg · Intraoral scan datasetB-IoU: 86.33 -> 88.81Improved
add Consistent Feature Learning (CFL) on top of two-view fusion (ablation)PMTSeg · Intraoral scan datasetmIoU: 93.82 -> 96.17Improved
add CFL on top of two-view fusion (ablation)PMTSeg · Intraoral scan datasetB-IoU: 88.81 -> 92.53Improved
add CFL on top of two-view fusion (ablation)PMTSeg · Intraoral scan datasetDSC: 96.78 -> 98.04Improved
use PMTSeg (photo guidance) instead of the best geometry-only baseline ATSLtooth segmentation · Intraoral scan datasetB-IoU: 90.53 -> 92.53Improved
use PMTSeg instead of image-point fusion baseline RPVNet (no CFL)tooth segmentation · Intraoral scan datasetmIoU: 92.99 -> 96.17Improved
use multi-view rendering (CrossTooth) instead of plain geometrytooth segmentation baselines · Intraoral scan datasetmIoU: 86.73 ± 10.1 mIoU vs 90.30 ± 3.8 for PTv3Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy