HPGNN: Using Hierarchical Graph Neural Networks for Outdoor Point Cloud Processing

TL;DR

This paper introduces HPGNN, a hierarchical graph neural network that efficiently processes large-scale outdoor LiDAR point clouds, preserving structural details and improving semantic segmentation accuracy over existing GNN methods.

Contribution

The paper proposes a novel hierarchical GNN architecture for outdoor point cloud processing, enabling multi-scale feature learning and better detail preservation.

Findings

Achieved +36.7 mIoU improvement on SemanticKITTI dataset.

Demonstrated superior performance over existing point-based and GNN models.

Enabled efficient processing of large-scale outdoor LiDAR data.

Abstract

Inspired by recent improvements in point cloud processing for autonomous navigation, we focus on using hierarchical graph neural networks for processing and feature learning over large-scale outdoor LiDAR point clouds. We observe that existing GNN based methods fail to overcome challenges of scale and irregularity of points in outdoor datasets. Addressing the need to preserve structural details while learning over a larger volume efficiently, we propose Hierarchical Point Graph Neural Network (HPGNN). It learns node features at various levels of graph coarseness to extract information. This enables to learn over a large point cloud while retaining fine details that existing point-level graph networks struggle to achieve. Connections between multiple levels enable a point to learn features in multiple scales, in a few iterations. We design HPGNN as a purely GNN-based approach, so that it offers modular expandability as seen with other point-based and Graph network baselines. To illustrate the improved processing capability, we compare previous point based and GNN models for semantic segmentation with our HPGNN, achieving a significant improvement for GNNs (+36.7 mIoU) on the SemanticKITTI dataset.