Lidar became an important component of the perception systems in autonomous driving. But challenges of training data acquisition and annotation made emphasized the role of the sensor to sensor domain adaptation. In this work, we address the problem of lidar upsampling. Learning on lidar point clouds is rather a challenging task due to their irregular and sparse structure. Here we propose a method for lidar point cloud upsampling which can reconstruct fine-grained lidar scan patterns. The key idea is to utilize edge-aware dense convolutions for both feature extraction and feature expansion. Additionally applying a more accurate Sliced Wasserstein Distance facilitates learning of the fine lidar sweep structures. This in turn enables our method to employ a one-stage upsampling paradigm without the need for coarse and fine reconstruction. We conduct several experiments to evaluate our method and demonstrate that it provides better upsampling.

翻译：激光雷达已成为自动驾驶感知系统的重要组成部分，但训练数据采集与标注的挑战凸显了传感器间域适应的重要性。本文针对激光雷达点云上采样问题展开研究。由于激光雷达点云具有不规则且稀疏的结构特征，对其进行学习是一项极具挑战性的任务。我们提出了一种能够重建精细扫描模式的激光雷达点云上采样方法，其核心思想是在特征提取与特征扩展环节均采用边缘感知密集卷积。同时，引入更精确的切片瓦瑟斯坦距离有助于学习精细的激光雷达扫描结构，这使得我们的方法能够采用单阶段上采样范式，无需进行粗重建与精细重建的两阶段处理。通过多项实验评估，我们验证了该方法能实现更优的上采样效果。