论文标题
Minkloc3D：基于点云的大规模地点识别
MinkLoc3D: Point Cloud Based Large-Scale Place Recognition
论文作者
论文摘要
本文提出了一种基于学习的方法，用于计算歧视性3D点云描述符，以实现位置识别目的。现有方法（例如PointNetVlad）基于无序的点云表示。他们使用PointNet作为提取本地功能的第一个处理步骤，后来将其汇总到全局描述符中。点网架构不太适合捕获局部几何结构。因此，最新方法通过添加不同的机制来捕获本地上下文信息，例如图形卷积网络或使用手工制作的功能来增强香草点网架构。我们提出了一种称为Minkloc3d的替代方法，以根据稀疏的体素化点云表示和稀疏的3D卷积来计算判别3D点云描述符。所提出的方法具有简单有效的体系结构。对标准基准测试的评估证明，Minkloc3D的表现要优于当前最新。我们的代码在项目网站上公开可用：https：//github.com/jac99/minkloc3d
The paper presents a learning-based method for computing a discriminative 3D point cloud descriptor for place recognition purposes. Existing methods, such as PointNetVLAD, are based on unordered point cloud representation. They use PointNet as the first processing step to extract local features, which are later aggregated into a global descriptor. The PointNet architecture is not well suited to capture local geometric structures. Thus, state-of-the-art methods enhance vanilla PointNet architecture by adding different mechanism to capture local contextual information, such as graph convolutional networks or using hand-crafted features. We present an alternative approach, dubbed MinkLoc3D, to compute a discriminative 3D point cloud descriptor, based on a sparse voxelized point cloud representation and sparse 3D convolutions. The proposed method has a simple and efficient architecture. Evaluation on standard benchmarks proves that MinkLoc3D outperforms current state-of-the-art. Our code is publicly available on the project website: https://github.com/jac99/MinkLoc3D
