Multi-Submap Implicit Neural SLAM with Local-to-Global Loop Closure for Large-Scale Scene Reconstruction
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new system for mapping and navigation called MSN-SLAM, designed to work well in large, complicated environments. They split the map into smaller parts to keep details without using too much memory and added methods to better track movement and correct errors when the viewpoint changes a lot. Their system also ensures different parts of the map stay consistent and was tested on both indoor and outdoor scenes, showing improved accuracy and reliability compared to previous methods. The authors plan to share their code publicly for others to use.
Neural Radiance FieldsSLAMloop closurepose estimationoptical flowsubmaprelocalizationmap consistencytrajectory driftdigital twinning
Authors
Tianchen Deng, Chongdi Wang, Nailin Wang, Lei Zhao, Ziqi Ma, Tianjun Zhang, Zhe Liu, Danwei Wang, Hesheng Wang
Abstract
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} .