TSegAgent: Zero-Shot Tooth Segmentation via Geometry-Aware Vision-Language Agents

TL;DR

TSegAgent introduces a zero-shot, geometry-aware approach for tooth segmentation that leverages foundation models and explicit dental structure reasoning, reducing annotation needs and improving generalization.

Contribution

It reformulates dental analysis as a zero-shot geometric reasoning task, integrating structural dental priors with foundation models for robust segmentation.

Findings

Achieves accurate tooth segmentation without task-specific training.

Demonstrates strong generalization across diverse dental scans.

Reduces annotation and computational costs.

Abstract

Automatic tooth segmentation and identification from intra-oral scanned 3D models are fundamental problems in digital dentistry, yet most existing approaches rely on task-specific 3D neural networks trained with densely annotated datasets, resulting in high annotation cost and limited generalization to scans from unseen sources. Thus, we propose TSegAgent, which addresses these challenges by reformulating dental analysis as a zero-shot geometric reasoning problem rather than a purely data-driven recognition task. The key idea is to combine the representational capacity of general-purpose foundation models with explicit geometric inductive biases derived from dental anatomy. Instead of learning dental-specific features, the proposed framework leverages multi-view visual abstraction and geometry-grounded reasoning to infer tooth instances and identities without task-specific training. By explicitly encoding structural constraints such as dental arch organization and volumetric relationships, the method reduces uncertainty in ambiguous cases and mitigates overfitting to particular shape distributions. Experimental results demonstrate that this reasoning-oriented formulation enables accurate and reliable tooth segmentation and identification with low computational and annotation cost, while exhibiting strong generalization across diverse and previously unseen dental scans.