PIN-SLAM：使用基于点的隐式神经表示实现全局地图一致性的 LiDAR SLAM
PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistency
AI总结：
本文提出 PIN-SLAM，利用稀疏可优化神经点表示隐式 SDF 地图，并通过无对应的点到隐式配准、神经特征回环检测与全局变形实现全局一致、紧凑且可实时运行的 LiDAR/RGB-D SLAM。
摘要：
准确且鲁棒的定位与建图是大多数自主机器人的核心组成部分。本文提出一种用于构建全局一致地图的 SLAM 系统，名为 PIN-SLAM，其基础是一种弹性且紧凑的基于点的隐式神经地图表示。该方法以距离测量为输入，在局部隐式有符号距离场的增量学习与基于当前局部地图的位姿估计之间交替进行；位姿估计采用无需对应的点到隐式模型配准。我们的隐式地图基于稀疏、可优化的神经点，这些点天然具有弹性，并能在闭环时随全局位姿调整而变形。回环也通过神经点特征进行检测。大量实验验证，PIN-SLAM 对多种环境具有鲁棒性，并可适配 LiDAR 和 RGB-D 相机等不同距离传感器。PIN-SLAM 取得了优于或持平于最先进 LiDAR 里程计或 SLAM 系统的位姿估计精度，同时优于近期的神经隐式 SLAM 方法，并维持更一致、高度紧凑的隐式地图，该地图可重建为准确且完整的网格。最后，得益于用于高效神经点索引的体素哈希，以及无需最近点关联的快速隐式地图配准，PIN-SLAM 可在中等性能 GPU 上以传感器帧率运行。代码将发布于：https://github.com/PRBonn/PIN_SLAM。
英文摘要：
Accurate and robust localization and mapping are essential components for most autonomous robots. In this paper, we propose a SLAM system for building globally consistent maps, called PIN-SLAM, that is based on an elastic and compact point-based implicit neural map representation. Taking range measurements as input, our approach alternates between incremental learning of the local implicit signed distance field and the pose estimation given the current local map using a correspondence-free, point-to-implicit model registration. Our implicit map is based on sparse optimizable neural points, which are inherently elastic and deformable with the global pose adjustment when closing a loop. Loops are also detected using the neural point features. Extensive experiments validate that PIN-SLAM is robust to various environments and versatile to different range sensors such as LiDAR and RGB-D cameras. PIN-SLAM achieves pose estimation accuracy better or on par with the state-of-the-art LiDAR odometry or SLAM systems and outperforms the recent neural implicit SLAM approaches while maintaining a more consistent, and highly compact implicit map that can be reconstructed as accurate and complete meshes. Finally, thanks to the voxel hashing for efficient neural points indexing and the fast implicit map-based registration without closest point association, PIN-SLAM can run at the sensor frame rate on a moderate GPU. Codes will be available at: https://github.com/PRBonn/PIN_SLAM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
