3DTeethSAM: Taming SAM2 for 3D Teeth Segmentation

TL;DR

This paper introduces 3DTeethSAM, an adaptation of SAM2 for 3D teeth segmentation, combining rendering, prompt embedding, mask refinement, and DGAP to achieve state-of-the-art accuracy on 3D dental models.

Contribution

The paper presents a novel adaptation of SAM2 for 3D teeth segmentation, including lightweight modules and DGAP to improve accuracy and training speed.

Findings

Achieved 91.90% IoU on 3DTeethSeg benchmark.

Enhanced segmentation accuracy with DGAP modules.

Established new state-of-the-art in 3D teeth segmentation.

Abstract

3D teeth segmentation, involving the localization of tooth instances and their semantic categorization in 3D dental models, is a critical yet challenging task in digital dentistry due to the complexity of real-world dentition. In this paper, we propose 3DTeethSAM, an adaptation of the Segment Anything Model 2 (SAM2) for 3D teeth segmentation. SAM2 is a pretrained foundation model for image and video segmentation, demonstrating a strong backbone in various downstream scenarios. To adapt SAM2 for 3D teeth data, we render images of 3D teeth models from predefined views, apply SAM2 for 2D segmentation, and reconstruct 3D results using 2D-3D projections. Since SAM2's performance depends on input prompts and its initial outputs often have deficiencies, and given its class-agnostic nature, we introduce three light-weight learnable modules: (1) a prompt embedding generator to derive prompt embeddings from image embeddings for accurate mask decoding, (2) a mask refiner to enhance SAM2's initial segmentation results, and (3) a mask classifier to categorize the generated masks. Additionally, we incorporate Deformable Global Attention Plugins (DGAP) into SAM2's image encoder. The DGAP enhances both the segmentation accuracy and the speed of the training process. Our method has been validated on the 3DTeethSeg benchmark, achieving an IoU of 91.90% on high-resolution 3D teeth meshes, establishing a new state-of-the-art in the field.