DF-SLAM: Dictionary Factors Representation for High-Fidelity Neural Implicit Dense Visual SLAM System

TL;DR

DF-SLAM introduces a neural implicit dense SLAM system using dictionary factors for scene representation, achieving high-fidelity reconstruction, efficient memory use, and real-time performance suitable for large-scale scenes.

Contribution

The paper presents a novel neural implicit dense SLAM approach employing dictionary factors, improving scene detail, memory efficiency, and real-time rendering over existing methods.

Findings

Superior scene detail reconstruction compared to prior methods

More efficient memory usage insensitive to scene size

Achieves real-time performance with high accuracy

Abstract

We introduce a high-fidelity neural implicit dense visual Simultaneous Localization and Mapping (SLAM) system, termed DF-SLAM. In our work, we employ dictionary factors for scene representation, encoding the geometry and appearance information of the scene as a combination of basis and coefficient factors. Compared to neural implicit dense visual SLAM methods that directly encode scene information as features, our method exhibits superior scene detail reconstruction capabilities and more efficient memory usage, while our model size is insensitive to the size of the scene map, making our method more suitable for large-scale scenes. Additionally, we employ feature integration rendering to accelerate color rendering speed while ensuring color rendering quality, further enhancing the real-time performance of our neural SLAM method. Extensive experiments on synthetic and real-world datasets demonstrate that our method is competitive with existing state-of-the-art neural implicit SLAM methods in terms of real-time performance, localization accuracy, and scene reconstruction quality. Our source code is available at https://github.com/funcdecl/DF-SLAM.