When 3D Partial Points Meets SAM: Tooth Point Cloud Segmentation with Sparse Labels

TL;DR

This paper introduces SAMTooth, a novel framework leveraging the Segment Anything Model (SAM) for efficient 3D tooth point cloud segmentation with extremely sparse labels, achieving results comparable to fully-supervised methods.

Contribution

The paper proposes a new framework that uses SAM's promptable segmentation and a confidence-aware prompt generation strategy for sparse label 3D segmentation.

Findings

With only 0.1% annotations, the method surpasses recent weakly supervised approaches.

The approach achieves performance comparable to fully-supervised methods.

The framework effectively exploits SAM's capabilities for 3D perception tasks.

Abstract

Tooth point cloud segmentation is a fundamental task in many orthodontic applications. Current research mainly focuses on fully supervised learning which demands expensive and tedious manual point-wise annotation. Although recent weakly-supervised alternatives are proposed to use weak labels for 3D segmentation and achieve promising results, they tend to fail when the labels are extremely sparse. Inspired by the powerful promptable segmentation capability of the Segment Anything Model (SAM), we propose a framework named SAMTooth that leverages such capacity to complement the extremely sparse supervision. To automatically generate appropriate point prompts for SAM, we propose a novel Confidence-aware Prompt Generation strategy, where coarse category predictions are aggregated with confidence-aware filtering. Furthermore, to fully exploit the structural and shape clues in SAM's outputs for assisting the 3D feature learning, we advance a Mask-guided Representation Learning that re-projects the generated tooth masks of SAM into 3D space and constrains these points of different teeth to possess distinguished representations. To demonstrate the effectiveness of the framework, we conduct experiments on the public dataset and surprisingly find with only 0.1\% annotations (one point per tooth), our method can surpass recent weakly supervised methods by a large margin, and the performance is even comparable to the recent fully-supervised methods, showcasing the significant potential of applying SAM to 3D perception tasks with sparse labels. Code is available at https://github.com/CUHK-AIM-Group/SAMTooth.