Accurate mapping of large-scale environments is an essential building block of most outdoor autonomous systems. Challenges of traditional mapping methods include the balance between memory consumption and mapping accuracy. This paper addresses the problem of achieving large-scale 3D reconstruction using implicit representations built from 3D LiDAR measurements. We learn and store implicit features through an octree-based, hierarchical structure, which is sparse and extensible. The implicit features can be turned into signed distance values through a shallow neural network. We leverage binary cross entropy loss to optimize the local features with the 3D measurements as supervision. Based on our implicit representation, we design an incremental mapping system with regularization to tackle the issue of forgetting in continual learning. Our experiments show that our 3D reconstructions are more accurate, complete, and memory-efficient than current state-of-the-art 3D mapping methods.

翻译：大规模环境的高精度地图构建是多数户外自主系统的核心基础组件。传统建图方法面临内存消耗与建图精度之间的平衡难题。本文针对利用3D激光雷达测量值构建隐式表示，实现大规模三维重建的问题展开研究。我们通过基于八叉树的层次化结构来学习并存储隐式特征，该结构具有稀疏性和可扩展性。这些隐式特征可通过浅层神经网络转化为有符号距离值。我们利用二元交叉熵损失函数，以3D测量值为监督信号来优化局部特征。基于所提出的隐式表示，我们设计了一种具有正则化机制的增量式建图系统，以解决持续学习中的遗忘问题。实验表明，与当前最先进的三维建图方法相比，我们的三维重建结果在精度、完整性和内存效率方面均更优。