When 3D Bounding-Box Meets SAM: Point Cloud Instance Segmentation with Weak-and-Noisy Supervision

TL;DR

This paper introduces CIP-WPIS, a novel method that combines 2D foundation models and 3D geometric priors to improve weakly-supervised 3D point cloud instance segmentation, especially under noisy bounding-box annotations.

Contribution

The paper proposes a new approach that leverages pretrained 2D models and 3D geometric information to enhance weakly-supervised segmentation accuracy in noisy conditions.

Findings

Achieves state-of-the-art results on Scannet-v2 and S3DIS.

Robust against noisy bounding-box annotations.

Effectively combines 2D prompts and 3D geometry for segmentation.

Abstract

Learning from bounding-boxes annotations has shown great potential in weakly-supervised 3D point cloud instance segmentation. However, we observed that existing methods would suffer severe performance degradation with perturbed bounding box annotations. To tackle this issue, we propose a complementary image prompt-induced weakly-supervised point cloud instance segmentation (CIP-WPIS) method. CIP-WPIS leverages pretrained knowledge embedded in the 2D foundation model SAM and 3D geometric prior to achieve accurate point-wise instance labels from the bounding box annotations. Specifically, CP-WPIS first selects image views in which 3D candidate points of an instance are fully visible. Then, we generate complementary background and foreground prompts from projections to obtain SAM 2D instance mask predictions. According to these, we assign the confidence values to points indicating the likelihood of points belonging to the instance. Furthermore, we utilize 3D geometric homogeneity provided by superpoints to decide the final instance label assignments. In this fashion, we achieve high-quality 3D point-wise instance labels. Extensive experiments on both Scannet-v2 and S3DIS benchmarks demonstrate that our method is robust against noisy 3D bounding-box annotations and achieves state-of-the-art performance.