LRGNet: Learnable Region Growing for Class-Agnostic Point Cloud Segmentation
It addresses the limitation of class-specific segmentation methods for robotics applications, offering a more generalizable approach, though it is incremental as it builds on region growing techniques.
The paper tackles the problem of class-agnostic point cloud segmentation for robots to understand environments, proposing a learnable region growing method that segments any object class without shape or size assumptions, achieving 1%-9% improvements over competitors on S3DIS and ScanNet datasets.
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.