论文标题
SOE-NET：基于点云的位置识别的自我注意力和方向编码网络
SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition
论文作者
论文摘要
我们解决了点云数据的位置识别问题，并引入了一个自我注意力和方向编码网络（SOE-net），该网络（SOE-net）充分探讨了点之间的关系，并将远程上下文纳入点的本地描述符。从八个方向捕获了八个方向的每个点的本地信息，在尖顶模块中捕获，而本地描述符之间的远程特征依赖项则以自我发项单元的形式捕获。此外，我们提出了一种新型的损失功能，称为硬性正面四弦损失（hphn Quadruplet），该损失功能比常用的度量学习损失更好。各种基准数据集的实验表明，所提出的网络的性能优于当前最新方法。我们的代码将在https://github.com/yan-xia/soe-net上公开发布。
We tackle the problem of place recognition from point cloud data and introduce a self-attention and orientation encoding network (SOE-Net) that fully explores the relationship between points and incorporates long-range context into point-wise local descriptors. Local information of each point from eight orientations is captured in a PointOE module, whereas long-range feature dependencies among local descriptors are captured with a self-attention unit. Moreover, we propose a novel loss function called Hard Positive Hard Negative quadruplet loss (HPHN quadruplet), that achieves better performance than the commonly used metric learning loss. Experiments on various benchmark datasets demonstrate superior performance of the proposed network over the current state-of-the-art approaches. Our code is released publicly at https://github.com/Yan-Xia/SOE-Net.
