SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition

PubDate: June 2021

Teams: 1Technical University of Munich 2Beijing Institute of Technology

Writers: Yan Xia1 Yusheng Xu1†Shuang Li2 Rui Wang1†Juan Du1 Daniel Cremers1 Uwe Stilla1

PDF: SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition

Abstract

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 selfattention 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 stateof-the-art approaches. Our code is released publicly at https://github.com/Yan-Xia/SOE-Net