ArchMap: Arch-Flattening and Knowledge-Guided Vision Language Model for Tooth Counting and Structured Dental Understanding

TL;DR

ArchMap introduces a training-free pipeline for robust structured dental understanding from intraoral 3D scans by integrating geometry-aware arch flattening, a Dental Knowledge Base (DKB), and schema-constrained vision–language inference. The approach converts irregular arch meshes into geometry-aligned multi-view representations, constrains reasoning with a hierarchical ontology, and uses a frozen VLM to produce ontology-consistent outputs across tooth counting, anatomical classification, dentition staging, and clinical conditions. Key contributions include (i) parabola-based arch estimation and normal-direction flattening for continuity-preserving 2D projections, (ii) a lightweight DKB encoding tooth count, dentition stages, and regions with semantic constraints, and (iii) a zero-training inference framework that enforces output contracts via DKB guidance. Evaluated on 1060 pre-/post-orthodontic cases, ArchMap achieves higher accuracy, reduced semantic drift, and greater stability under artifact-prone conditions, demonstrating practical potential for clinical deployment in digital orthodontics.

Abstract

A structured understanding of intraoral 3D scans is essential for digital orthodontics. However, existing deep-learning approaches rely heavily on modality-specific training, large annotated datasets, and controlled scanning conditions, which limit generalization across devices and hinder deployment in real clinical workflows. Moreover, raw intraoral meshes exhibit substantial variation in arch pose, incomplete geometry caused by occlusion or tooth contact, and a lack of texture cues, making unified semantic interpretation highly challenging. To address these limitations, we propose ArchMap, a training-free and knowledge-guided framework for robust structured dental understanding. ArchMap first introduces a geometry-aware arch-flattening module that standardizes raw 3D meshes into spatially aligned, continuity-preserving multi-view projections. We then construct a Dental Knowledge Base (DKB) encoding hierarchical tooth ontology, dentition-stage policies, and clinical semantics to constrain the symbolic reasoning space. We validate ArchMap on 1060 pre-/post-orthodontic cases, demonstrating robust performance in tooth counting, anatomical partitioning, dentition-stage classification, and the identification of clinical conditions such as crowding, missing teeth, prosthetics, and caries. Compared with supervised pipelines and prompted VLM baselines, ArchMap achieves higher accuracy, reduced semantic drift, and superior stability under sparse or artifact-prone conditions. As a fully training-free system, ArchMap demonstrates that combining geometric normalization with ontology-guided multimodal reasoning offers a practical and scalable solution for the structured analysis of 3D intraoral scans in modern digital orthodontics.

Figures (2)

• Figure 1: ArchMap workflow (left to right).Left: Geometry-aware dental arch flattening—parabola-based curve estimation, normal-direction surface flattening, and continuity-preserving rendering to obtain standardized front/back/bottom views. Middle: Dental Knowledge Base (DKB)—a lightweight hierarchical ontology defining tooth count, dentition stages, regional and size categories, and semantic constraints. Right: Schema-constrained vision–language inference—a four-stage procedure (Query → Retrieve → Generate → Output) executed on a frozen VLM to produce a fixed-structure JSON report.
• Figure 2: Qualitative observations of four representative clinical conditions: Dental Crowding, Missing Teeth, Denture, and Dental Caries. Each case is shown from the front, back, and bottom views; red boxes mark regions attended by the model. Dental Crowding—G1: two pairs of adjacent teeth are crowded side by side; G2: the anterior teeth are crowded. Missing Teeth—G1: two positions show missing teeth; G2: one position shows a missing tooth. Denture: one site indicates a denture. Dental Caries: one site shows dental caries.