发表机构
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University; Carnegie Mellon University; School of Electrical and Electronic Engineering, Nanyang Technological University（上海交通大学自动化与智能感知学院; 卡内基梅隆大学; 南洋理工大学电气与电子工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种带多子图架构与双层回环检测机制的神经SLAM系统，结合渐进式建图、光流跟踪、局部到全局回环及子图间在线蒸馏算法，在大规模场景重建性能上优于现有最优方法。
AI 中文摘要
基于神经辐射场（NeRF）的SLAM在小规模场景重建中已展现出出色效果，但由于灾难性遗忘和累积轨迹漂移，将这些方法扩展到广阔、复杂的环境仍具挑战性。本文提出一种鲁棒的大规模神经SLAM系统，具有多子图架构和双层回环检测机制。具体而言，我们提出一种渐进式建图策略，动态分配神经子图以维持高保真表示，同时避免内存爆炸。为实现鲁棒位姿估计，集成了基于光流的跟踪模块以处理剧烈运动。为解决全局一致性问题，我们引入一种局部到全局回环检测框架，利用基础模型进行高性能全局描述子提取，显著提升了不同视角下的重定位精度。此外，在后端优化期间设计了子图间在线蒸馏算法，以强制重叠子图边界间的几何和外观一致性。为验证该系统，我们开发了定制化手持机电平台，并在公共基准及我们的大规模室内外数据集上进行了广泛评估。包括直接部署到车载计算单元在内的实验结果表明，我们的方法在重建质量和定位鲁棒性方面优于现有最优神经SLAM方法，为实际机器人感知和数字孪生提供了可扩展的解决方案。我们将在公开网址上公开发布代码。
英文摘要
Neural Radiance Fields (NeRF)-based SLAM has demonstrated impressive results in small-scale scene reconstruction, yet scaling these methods to extensive, complex environments remains challenging due to catastrophic forgetting and accumulated trajectory drift. This paper presents a robust, large-scale neural SLAM system featuring a multi-submap architecture and a dual-tier loop closure mechanism. Specifically, we propose a progressive mapping strategy that dynamically allocates neural submaps to maintain high-fidelity representations without memory explosion. For robust pose estimation, an optical-flow-based tracking module is integrated to handle aggressive motions. To address global consistency, we introduce a local-to-global loop closure framework leveraging the foundation model for high-performance global descriptor extraction, significantly enhancing relocalization accuracy under varying viewpoints. Furthermore, an inter-submap online distillation algorithm is designed during back-end optimization to enforce geometric and appearance consistency across overlapping submap boundaries. To validate the system, we developed a customized handheld mechatronic platform and conducted extensive evaluations on both public benchmarks and our large-scale indoor-outdoor datasets. Experimental results, including direct deployment on an onboard computing unit, demonstrate that our approach outperforms state-of-the-art neural SLAM methods in reconstruction quality and localization robustness, providing a scalable solution for real-world robotic perception and digital twinning. We will release the code publicly on \href{https://github.com/dtc111111/MSN-SLAM}{https://github.com/dtc111111/MSN-SLAM} .
