Recently, significant progress has been achieved in sensing real large-scale outdoor 3D environments, particularly by using modern acquisition equipment such as LiDAR sensors. Unfortunately, they are fundamentally limited in their ability to produce dense, complete 3D scenes. To address this issue, recent learning-based methods integrate neural implicit representations and optimizable feature grids to approximate surfaces of 3D scenes. However, naively fitting samples along raw LiDAR rays leads to noisy 3D mapping results due to the nature of sparse, conflicting LiDAR measurements. Instead, in this work we depart from fitting LiDAR data exactly, instead letting the network optimize a non-metric monotonic implicit field defined in 3D space. To fit our field, we design a learning system integrating a monotonicity loss that enables optimizing neural monotonic fields and leverages recent progress in large-scale 3D mapping. Our algorithm achieves high-quality dense 3D mapping performance as captured by multiple quantitative and perceptual measures and visual results obtained for Mai City, Newer College, and KITTI benchmarks. The code of our approach will be made publicly available.

翻译：近期，利用LiDAR传感器等现代采集设备感知真实大规模室外三维环境取得了显著进展。然而，这些设备在生成稠密、完整的三维场景方面存在根本性局限。为解决该问题，现有基于学习的方法通过融合神经隐式表示与可优化特征网格来近似三维场景表面。但直接沿原始LiDAR射线对样本进行朴素拟合，会因LiDAR测量数据的稀疏性与冲突特性导致三维映射结果存在噪声。与此不同，本文摒弃了对LiDAR数据的精确拟合，转而让网络优化定义于三维空间中的非度量单调隐式场。为拟合该场域，我们设计了一个包含单调性损失函数的学习系统，该系统既能优化神经单调场，又可借鉴大规模三维映射领域的最新进展。实验表明，本算法在Mai City、Newer College和KITTI基准数据集上，通过多项定量指标、感知度量及可视化结果均展现出高质量稠密三维映射性能。本方法代码将公开发布。