DF-SLAM: Dictionary Factors Representation for High-Fidelity Neural Implicit Dense Visual SLAM System
This work addresses the challenge of scalable and detailed scene reconstruction in neural implicit SLAM for robotics and AR/VR applications, though it appears incremental as it builds on existing neural implicit SLAM frameworks.
The authors tackled the problem of high-fidelity dense visual SLAM by introducing DF-SLAM, which uses dictionary factors for scene representation, resulting in superior detail reconstruction, efficient memory usage, and competitive real-time performance compared to state-of-the-art methods.
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.