Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Mining

TL;DR

This paper presents a semi-supervised framework for point cloud instance segmentation that reduces annotation costs by leveraging unlabeled data through bounding box proposals, self-supervision, and mask mining techniques.

Contribution

It introduces the first semi-supervised point cloud instance segmentation framework using bounding boxes and proposes novel modules for mask mining and refinement.

Findings

Achieves competitive performance on ScanNet v2 dataset

Effectively leverages unlabeled data with semi-supervised learning

Introduces novel modules for mask mining and mask refinement

Abstract

Point cloud instance segmentation has achieved huge progress with the emergence of deep learning. However, these methods are usually data-hungry with expensive and time-consuming dense point cloud annotations. To alleviate the annotation cost, unlabeled or weakly labeled data is still less explored in the task. In this paper, we introduce the first semi-supervised point cloud instance segmentation framework (SPIB) using both labeled and unlabelled bounding boxes as supervision. To be specific, our SPIB architecture involves a two-stage learning procedure. For stage one, a bounding box proposal generation network is trained under a semi-supervised setting with perturbation consistency regularization (SPCR). The regularization works by enforcing an invariance of the bounding box predictions over different perturbations applied to the input point clouds, to provide self-supervision for network learning. For stage two, the bounding box proposals with SPCR are grouped into some subsets, and the instance masks are mined inside each subset with a novel semantic propagation module and a property consistency graph module. Moreover, we introduce a novel occupancy ratio guided refinement module to refine the instance masks. Extensive experiments on the challenging ScanNet v2 dataset demonstrate our method can achieve competitive performance compared with the recent fully-supervised methods.