Modeling scene geometry using implicit neural representation has revealed its advantages in accuracy, flexibility, and low memory usage. Previous approaches have demonstrated impressive results using color or depth images but still have difficulty handling poor light conditions and large-scale scenes. Methods taking global point cloud as input require accurate registration and ground truth coordinate labels, which limits their application scenarios. In this paper, we propose a new method that uses sparse LiDAR point clouds and rough odometry to reconstruct fine-grained implicit occupancy field efficiently within a few minutes. We introduce a new loss function that supervises directly in 3D space without 2D rendering, avoiding information loss. We also manage to refine poses of input frames in an end-to-end manner, creating consistent geometry without global point cloud registration. As far as we know, our method is the first to reconstruct implicit scene representation from LiDAR-only input. Experiments on synthetic and real-world datasets, including indoor and outdoor scenes, prove that our method is effective, efficient, and accurate, obtaining comparable results with existing methods using dense input.

翻译：使用隐式神经表示建模场景几何在精度、灵活性和低内存消耗方面展现出优势。先前的方法利用彩色或深度图像取得了令人印象深刻的结果，但在处理光照条件差和大规模场景时仍存在困难。以全局点云作为输入的方法需要精确配准和真实坐标标签，限制了其应用场景。本文提出了一种新方法，该方法利用稀疏激光雷达点云和粗略里程计，在几分钟内高效重建细粒度隐式占用场。我们引入了一种新型损失函数，在不经过二维渲染的情况下直接对三维空间进行监督，避免了信息丢失。同时，我们以端到端方式优化输入帧的位姿，无需全局点云配准即可生成一致的几何结构。据我们所知，我们的方法是首个仅基于激光雷达输入重建隐式场景表示的方法。在包含室内外场景的合成和真实数据集上的实验证明，我们的方法有效、高效且精确，能够获得与使用密集输入的现有方法相当的结果。