Neural Graph Map: Dense Mapping with Efficient Loop Closure Integration

TL;DR

This paper introduces Neural Graph Map, a scalable neural mapping method that efficiently incorporates loop closures in large-scale scenes, outperforming existing approaches in quality and runtime.

Contribution

It presents a novel neural mapping framework using lightweight neural fields anchored to a pose graph, enabling efficient large-scale loop closure integration and improved scalability.

Findings

Successfully integrates large-scale loop closures

Outperforms state-of-the-art methods in quality and runtime

Demonstrates building-scale mapping with multiple loop closures

Abstract

Neural field-based SLAM methods typically employ a single, monolithic field as their scene representation. This prevents efficient incorporation of loop closure constraints and limits scalability. To address these shortcomings, we propose a novel RGB-D neural mapping framework in which the scene is represented by a collection of lightweight neural fields which are dynamically anchored to the pose graph of a sparse visual SLAM system. Our approach shows the ability to integrate large-scale loop closures, while requiring only minimal reintegration. Furthermore, we verify the scalability of our approach by demonstrating successful building-scale mapping taking multiple loop closures into account during the optimization, and show that our method outperforms existing state-of-the-art approaches on large scenes in terms of quality and runtime. Our code is available open-source at https://github.com/KTH-RPL/neural_graph_mapping.