LRGNet: Learnable Region Growing for Class-Agnostic Point Cloud Segmentation

TL;DR

LRGNet introduces a learnable, class-agnostic region growing neural network that effectively segments various object classes in 3D point clouds without prior shape assumptions, outperforming existing methods.

Contribution

The paper presents a novel deep learning approach for class-agnostic point cloud segmentation using learnable region growing, enabling flexible and generalizable instance segmentation.

Findings

Outperforms competing methods by 1%-9% on multiple metrics

Effective on S3DIS and ScanNet datasets

Handles diverse object classes without shape assumptions

Abstract

3D point cloud segmentation is an important function that helps robots understand the layout of their surrounding environment and perform tasks such as grasping objects, avoiding obstacles, and finding landmarks. Current segmentation methods are mostly class-specific, many of which are tuned to work with specific object categories and may not be generalizable to different types of scenes. This research proposes a learnable region growing method for class-agnostic point cloud segmentation, specifically for the task of instance label prediction. The proposed method is able to segment any class of objects using a single deep neural network without any assumptions about their shapes and sizes. The deep neural network is trained to predict how to add or remove points from a point cloud region to morph it into incrementally more complete regions of an object instance. Segmentation results on the S3DIS and ScanNet datasets show that the proposed method outperforms competing methods by 1%-9% on 6 different evaluation metrics.