Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds

TL;DR

This paper introduces a deep learning architecture for 3D semantic segmentation of point clouds, utilizing novel neighborhood grouping and specialized loss functions to improve feature learning and achieve state-of-the-art results.

Contribution

It presents a new method that defines point neighborhoods in both world and feature spaces, with dedicated loss functions to enhance segmentation accuracy.

Findings

Achieves state-of-the-art performance on indoor datasets.

Effective neighborhood grouping improves feature learning.

Demonstrates robustness on outdoor datasets.

Abstract

In this paper, we present a deep learning architecture which addresses the problem of 3D semantic segmentation of unstructured point clouds. Compared to previous work, we introduce grouping techniques which define point neighborhoods in the initial world space and the learned feature space. Neighborhoods are important as they allow to compute local or global point features depending on the spatial extend of the neighborhood. Additionally, we incorporate dedicated loss functions to further structure the learned point feature space: the pairwise distance loss and the centroid loss. We show how to apply these mechanisms to the task of 3D semantic segmentation of point clouds and report state-of-the-art performance on indoor and outdoor datasets.