FlashSLAM: Accelerated RGB-D SLAM for Real-Time 3D Scene Reconstruction with Gaussian Splatting
This provides a more efficient and robust solution for real-time 3D reconstruction in applications like robotics and AR/VR, though it appears incremental as it builds on existing 3DGS-based SLAM methods.
FlashSLAM tackles the problem of slow and inaccurate 3D scene reconstruction in sparse view settings and during large camera movements by combining 3D Gaussian Splatting with fast vision-based camera tracking, achieving a 90% reduction in tracking time and up to 92% improvement in tracking accuracy over previous methods.
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.