NGEL-SLAM：基于神经隐式表示的全局一致低延迟SLAM系统
NGEL-SLAM: Neural Implicit Representation-based Global Consistent Low-Latency SLAM System
AI总结：
针对现有神经隐式SLAM全局一致性和延迟不足，提出NGEL-SLAM，融合特征跟踪回环与多神经隐式场及八叉树表示，实现低延迟全局一致的高保真建图，精度达最先进水平。
摘要：
神经隐式表示已成为在同步定位与建图（SLAM）中提供密集几何信息的 promising 解决方案。然而，现有方法在全局一致性和低延迟方面存在不足。本文提出 NGEL-SLAM 以应对上述挑战。为确保全局一致性，我们的系统利用基于传统特征跟踪模块并集成回环检测。此外，我们通过使用多个神经隐式场来表示场景，从而维护全局一致的地图，能够快速调整回环。同时，我们的系统通过基于八叉树的隐式表示实现快速收敛。对回环的快速响应与快速收敛的结合，使我们的系统成为真正低延迟且实现全局一致性的系统。我们的系统能够渲染高保真 RGB-D 图像，并提取密集且完整的表面。在合成和真实世界数据集上的实验表明，我们的系统在保持低延迟的同时，达到了最先进的跟踪和建图精度。
英文摘要：
Neural implicit representations have emerged as a promising solution for providing dense geometry in Simultaneous Localization and Mapping (SLAM). However, existing methods in this direction fall short in terms of global consistency and low latency. This paper presents NGEL-SLAM to tackle the above challenges. To ensure global consistency, our system leverages a traditional feature-based tracking module that incorporates loop closure. Additionally, we maintain a global consistent map by representing the scene using multiple neural implicit fields, enabling quick adjustment to the loop closure. Moreover, our system allows for fast convergence through the use of octree-based implicit representations. The combination of rapid response to loop closure and fast convergence makes our system a truly low-latency system that achieves global consistency. Our system enables rendering high-fidelity RGB-D images, along with extracting dense and complete surfaces. Experiments on both synthetic and real-world datasets suggest that our system achieves state-of-the-art tracking and mapping accuracy while maintaining low latency.
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。
