点云深度学习：Point-GNN：CVPR 2020论文中3D目标检测的图神经网络方法

需积分: 0 192 浏览量更新于2024-08-03 收藏 1.09MB PDF 举报

本文档《Shi_Point-GNN_Graph_Neural_Network_for_3D_Object_Detection_in_a_CVPR_2020_paper.pdf》主要探讨了在计算机视觉(CV)领域中的3D物体检测方法，特别是在使用激光雷达(LiDAR)点云数据时。作者北京石和Ragunathan (Raj) Rajkumar来自卡内基梅隆大学(Carnegie Mellon University)，他们在论文中提出了一个名为Point-GNN的图神经网络架构，旨在有效地处理点云数据，并进行准确的物体分类和形状预测。首先，作者强调了在3D环境中进行物体检测的重要性，这对于机器人技术、自动驾驶和机器人导航等应用至关重要。传统的3D物体检测通常依赖于深度图像或融合多种传感器数据的方法，但这篇工作着重于单个点云数据的分析。 Point-GNN的设计核心在于构建一个固定半径的邻域图，将点云中的每个点作为一个节点，通过邻居关系进行信息传播。这种图结构有助于捕捉点云中点与点之间的局部几何关系，从而提升对物体特征的理解。为了减少因物体位置变化导致的检测偏差，作者提出了自动注册机制，使得网络能够适应不同的视角和姿态变化。此外，Point-GNN中还包括一个设计巧妙的合并和评分操作，它能够整合来自图中多个节点的检测结果，提高整体检测的准确性。这个过程考虑了不同部分的信息交互，确保了物体检测的完整性。在实验部分，作者展示了Point-GNN在KITTI基准测试上的卓越性能，证明了仅凭点云数据就能达到领先的检测精度，并且在某些情况下甚至超越了那些依赖多传感器融合的算法。这表明，图神经网络作为一种新兴的方法，在3D物体检测任务中具有巨大的潜力。论文的贡献包括提出了一种有效的图神经网络架构，以及一套完整的处理策略，使得3D物体检测在单一的点云输入下也能实现高效和精确。代码已开源，可供其他研究者进一步研究和改进。这一研究对于推动3D计算机视觉领域的发展具有重要意义，也为未来基于图神经网络的3D物体检测技术的发展奠定了基础。

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

Weijing Shi and Ragunathan (Raj) Rajkumar

Carnegie Mellon University

Pittsburgh, PA 15213

{weijings, rajkumar}@cmu.edu

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 ra-

dius near-neighbors graph. We design a graph neural net-

work, 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 merg-

ing and scoring operation to combine detections from mul-

tiple vertices accurately. Our experiments on the KITTI

benchmark show the proposed approach achieves leading

accuracy using the point cloud alone and can even sur-

pass fusion-based algorithms. Our results demonstrate the

potential of using the graph neural network as a new ap-

proach for 3D object detection. The code is available at

https://github.com/WeijingShi/Point-GNN.

1. Introduction

Understanding the 3D environment is vital in robotic per-

ception. A point cloud that composes a set of points in space

is a widely-used format for 3D sensors such as LiDAR. De-

tecting objects accurately from a point cloud is crucial in

applications such as autonomous driving.

Convolutional neural networks that detect objects from

images rely on the convolution operation. While the con-

volution operation is efﬁcient, it requires a regular grid as

input. Unlike an image, a point cloud is typically sparse and

not spaced evenly on a regular grid. Placing a point cloud on

a regular grid generates an uneven number of points in the

grid cells. Applying the same convolution operation on such

a grid leads to potential information loss in the crowded

cells or wasted computation in the empty cells.

Recent breakthroughs in using neural networks [

3][22]

allow an unordered set of points as input. Studies take

advantage of this type of neural network to extract point

cloud features without mapping the point cloud to a grid.

However, they typically need to sample and group points

Figure 1. Three point cloud representations and their common pro-

cessing methods.

iteratively to create a point set representation. The re-

peated grouping and sampling on a large point cloud can

be computationally costly. Recent 3D detection approaches

[

10][21][16] often take a hybrid approach to use a grid and

a set representation in different stages. Although they show

some promising results, such hybrid strategies may suffer

the shortcomings of both representations.

In this work, we propose to use a graph as a compact

representation of a point cloud and design a graph neural

network called Point-GNN to detect objects. We encode

the point cloud natively in a graph by using the points as the

graph vertices. The edges of the graph connect neighbor-

hood points that lie within a ﬁxed radius, which allows fea-

ture information to ﬂow between neighbors. Such a graph

representation adapts to the structure of a point cloud di-

rectly without the need to make it regular. A graph neural

network reuses the graph edges in every layer, and avoids

grouping and sampling the points repeatedly.

Studies [

15][9][2][17] have looked into using graph

neural network for the classiﬁcation and the semantic seg-

mentation of a point cloud. However, little research has

looked into using a graph neural network for the 3D object

detection in a point cloud. Our work demonstrates the fea-

sibility of using a GNN for highly accurate object detection

in a point cloud.

Our proposed graph neural network Point-GNN takes

the point graph as its input. It outputs the category and

bounding boxes of the objects to which each vertex be-

longs. Point-GNN is a one-stage detection method that de-

tects multiple objects in a single shot. To reduce the trans-

lation variance in a graph neural network, we introduce an

1711

下载后可阅读完整内容，剩余8页未读，立即下载

qq_48785109

粉丝: 1
资源: 1

点云深度学习：Point-GNN：CVPR 2020论文中3D目标检测的图神经网络方法

安装torch_sparse-0.6.16与指定版本PyTorch指南

安装指南：如何搭配PyTorch和CUDA使用torch_cluster-1.5.9

如何安装torch_cluster-1.5.4版本包及指定torch版本

Point-GNN:点神经网络

visdial-gnn:PyTorch代码用于通过结构观察和部分观察来推理视觉对话框

近期必读的5篇AI顶会CVPR 2020（图神经网络GNN) 相关论文.zip

5篇CVPR 2020相关论文【场景图+图神经网络（SG+GNN）】

Interesting Top-Conference Papers on Video Analysis

GPT-GNN: 图神经网络的生成式预训练代码解析

基于labview的改变字体大小源码.zip

最新资源