FGS-SLAM: Fourier-based Gaussian Splatting for Real-time SLAM with Sparse and Dense Map Fusion

FGS-SLAM: Fourier-based Gaussian Splatting for Real-time SLAM with Sparse and Dense Map Fusion Y ansong Xu 1, 2, Junlin Li 1, Wei Zhang 1, Siyu Chen 1, 2, Shengyong Zhang 1, Y uquan Leng 3, Weijia Zhou 1 Abstract -- 3D gaussian splatting has advanced simultaneous localization and mapping (SLAM) technology by enabling real-time positioning and the construction of high-fidelity maps. However, the uncertainty in gaussian position and initialization parameters introduces challenges, often requiring extensive iterative convergence and resulting in redundant or insufficient gaussian representations. T o address this, we introduce a novel adaptive densification method based on Fourier frequency domain analysis to establish gaussian priors for rapid convergence. Additionally, we propose constructing independent and unified sparse and dense maps, where a sparse map supports efficient tracking via Generalized Iterative Closest Point (GICP) and a dense map creates high-fidelity visual representations. This is the first SLAM system leveraging frequency domain analysis to achieve high-quality gaussian mapping in real-time. Experimental results demonstrate an average frame rate of 36 FPS on Replica and TUM RGB-D datasets, achieving competitive accuracy in both localization and mapping. I NRODUCTION With the rapid development of fields such as robotics [1], augmented reality (AR), and drones, there is an increasing demand for efficient and accurate 3D environmental perception. As a result, the importance of Simultaneous Localization and Mapping (SLAM) technology in these applications has grown significantly. The main challenge of SLAM is achieving both autonomous localization and 3D map construction in unknown environments. However, traditional SLAM methods still face significant challenges in balancing real-time performance and scene accuracy.