Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud

TL;DR

This paper introduces Point-GNN, a graph neural network that detects 3D objects from LiDAR point clouds by encoding points into a graph and applying novel mechanisms for translation invariance and detection merging, achieving state-of-the-art results.

Contribution

The paper presents a novel graph neural network architecture for 3D object detection in point clouds, including auto-registration and detection merging techniques.

Findings

Achieves leading accuracy on KITTI benchmark

Surpasses fusion-based algorithms using only point cloud data

Demonstrates the effectiveness of graph neural networks for 3D detection

Abstract

In this paper, we propose a graph neural network to detect objects from a LiDAR point cloud. Towards this end, we encode the point cloud efficiently in a fixed radius near-neighbors graph. We design a graph neural network, named Point-GNN, to predict the category and shape of the object that each vertex in the graph belongs to. In Point-GNN, we propose an auto-registration mechanism to reduce translation variance, and also design a box merging and scoring operation to combine detections from multiple vertices accurately. Our experiments on the KITTI benchmark show the proposed approach achieves leading accuracy using the point cloud alone and can even surpass fusion-based algorithms. Our results demonstrate the potential of using the graph neural network as a new approach for 3D object detection. The code is available https://github.com/WeijingShi/Point-GNN.