Research

Paper

AI LLM March 17, 2026

IOSVLM: A 3D Vision-Language Model for Unified Dental Diagnosis from Intraoral Scans

Authors

Huimin Xiong, Zijie Meng, Tianxiang Hu, Chenyi Zhou, Yang Feng, Zuozhu Liu

Abstract

3D intraoral scans (IOS) are increasingly adopted in routine dentistry due to abundant geometric evidence, and unified multi-disease diagnosis is desirable for clinical documentation and communication. While recent works introduce dental vision-language models (VLMs) to enable unified diagnosis and report generation on 2D images or multi-view images rendered from IOS, they do not fully leverage native 3D geometry. Such work is necessary and also challenging, due to: (i) heterogeneous scan forms and the complex IOS topology, (ii) multi-disease co-occurrence with class imbalance and fine-grained morphological ambiguity, (iii) limited paired 3D IOS-text data. Thus, we present IOSVLM, an end-to-end 3D VLM that represents scans as point clouds and follows a 3D encoder-projector-LLM design for unified diagnosis and generative visual question-answering (VQA), together with IOSVQA, a large-scale multi-source IOS diagnosis VQA dataset comprising 19,002 cases and 249,055 VQA pairs over 23 oral diseases and heterogeneous scan types. To address the distribution gap between color-free IOS data and color-dependent 3D pre-training, we propose a geometry-to-chromatic proxy that stabilizes fine-grained geometric perception and cross-modal alignment. A two-stage curriculum training strategy further enhances robustness. IOSVLM consistently outperforms strong baselines, achieving gains of at least +9.58% macro accuracy and +1.46% macro F1, indicating the effectiveness of direct 3D geometry modeling for IOS-based diagnosis.

Metadata

arXiv ID: 2603.16781
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-17
Fetched: 2026-03-18 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.16781v1</id>\n    <title>IOSVLM: A 3D Vision-Language Model for Unified Dental Diagnosis from Intraoral Scans</title>\n    <updated>2026-03-17T16:57:02Z</updated>\n    <link href='https://arxiv.org/abs/2603.16781v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.16781v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>3D intraoral scans (IOS) are increasingly adopted in routine dentistry due to abundant geometric evidence, and unified multi-disease diagnosis is desirable for clinical documentation and communication. While recent works introduce dental vision-language models (VLMs) to enable unified diagnosis and report generation on 2D images or multi-view images rendered from IOS, they do not fully leverage native 3D geometry. Such work is necessary and also challenging, due to: (i) heterogeneous scan forms and the complex IOS topology, (ii) multi-disease co-occurrence with class imbalance and fine-grained morphological ambiguity, (iii) limited paired 3D IOS-text data. Thus, we present IOSVLM, an end-to-end 3D VLM that represents scans as point clouds and follows a 3D encoder-projector-LLM design for unified diagnosis and generative visual question-answering (VQA), together with IOSVQA, a large-scale multi-source IOS diagnosis VQA dataset comprising 19,002 cases and 249,055 VQA pairs over 23 oral diseases and heterogeneous scan types. To address the distribution gap between color-free IOS data and color-dependent 3D pre-training, we propose a geometry-to-chromatic proxy that stabilizes fine-grained geometric perception and cross-modal alignment. A two-stage curriculum training strategy further enhances robustness. IOSVLM consistently outperforms strong baselines, achieving gains of at least +9.58% macro accuracy and +1.46% macro F1, indicating the effectiveness of direct 3D geometry modeling for IOS-based diagnosis.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-17T16:57:02Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Huimin Xiong</name>\n    </author>\n    <author>\n      <name>Zijie Meng</name>\n    </author>\n    <author>\n      <name>Tianxiang Hu</name>\n    </author>\n    <author>\n      <name>Chenyi Zhou</name>\n    </author>\n    <author>\n      <name>Yang Feng</name>\n    </author>\n    <author>\n      <name>Zuozhu Liu</name>\n    </author>\n  </entry>"
}