Neural Graph Map: Dense Mapping with Efficient Loop Closure Integration
This work addresses scalability and loop closure issues in neural SLAM for robotics and AR/VR applications, representing an incremental improvement over existing methods.
The paper tackles the problem of inefficient loop closure integration and limited scalability in neural field-based SLAM by proposing a framework that uses lightweight neural fields anchored to a sparse visual SLAM pose graph. The result shows successful large-scale mapping with minimal reintegration, outperforming state-of-the-art methods in quality and runtime on large scenes.
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.