FlashSLAM: Accelerated RGB-D SLAM for Real-Time 3D Scene Reconstruction with Gaussian Splatting

TL;DR

FlashSLAM introduces a fast, robust RGB-D SLAM method using 3D Gaussian Splatting and a vision-based tracking approach, significantly improving speed and accuracy in real-time 3D scene reconstruction, even with sparse data and noisy sensors.

Contribution

It combines 3D Gaussian Splatting with a pretrained feature matching model for rapid pose estimation, reducing tracking time by 90% and improving accuracy in sparse view settings.

Findings

Achieves up to 92% improvement in tracking accuracy over previous methods.

Reduces camera tracking time to under 80 ms, enabling real-time performance.

Demonstrates robustness across synthetic and real-world environments.

Abstract

We present FlashSLAM, a novel SLAM approach that leverages 3D Gaussian Splatting for efficient and robust 3D scene reconstruction. Existing 3DGS-based SLAM methods often fall short in sparse view settings and during large camera movements due to their reliance on gradient descent-based optimization, which is both slow and inaccurate. FlashSLAM addresses these limitations by combining 3DGS with a fast vision-based camera tracking technique, utilizing a pretrained feature matching model and point cloud registration for precise pose estimation in under 80 ms - a 90% reduction in tracking time compared to SplaTAM - without costly iterative rendering. In sparse settings, our method achieves up to a 92% improvement in average tracking accuracy over previous methods. Additionally, it accounts for noise in depth sensors, enhancing robustness when using unspecialized devices such as smartphones. Extensive experiments show that FlashSLAM performs reliably across both sparse and dense settings, in synthetic and real-world environments. Evaluations on benchmark datasets highlight its superior accuracy and efficiency, establishing FlashSLAM as a versatile and high-performance solution for SLAM, advancing the state-of-the-art in 3D reconstruction across diverse applications.