Towards Real-Time Gaussian Splatting: Accelerating 3DGS through Photometric SLAM

TL;DR

This paper explores integrating 3D Gaussian Splatting with photometric SLAM to accelerate training and enable real-time 3D reconstruction on mobile devices, addressing current speed and performance limitations.

Contribution

It introduces a novel integration of 3DGS with Direct Sparse Odometry, significantly reducing training time and paving the way for real-time SLAM systems on mobile hardware.

Findings

Using Direct Sparse Odometry point clouds shortens training time

Preliminary results show potential for real-time 3DGS-based SLAM

Integration improves speed without compromising reconstruction quality

Abstract

Initial applications of 3D Gaussian Splatting (3DGS) in Visual Simultaneous Localization and Mapping (VSLAM) demonstrate the generation of high-quality volumetric reconstructions from monocular video streams. However, despite these promising advancements, current 3DGS integrations have reduced tracking performance and lower operating speeds compared to traditional VSLAM. To address these issues, we propose integrating 3DGS with Direct Sparse Odometry, a monocular photometric SLAM system. We have done preliminary experiments showing that using Direct Sparse Odometry point cloud outputs, as opposed to standard structure-from-motion methods, significantly shortens the training time needed to achieve high-quality renders. Reducing 3DGS training time enables the development of 3DGS-integrated SLAM systems that operate in real-time on mobile hardware. These promising initial findings suggest further exploration is warranted in combining traditional VSLAM systems with 3DGS.