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

Abstract-- Initial applications of 3D Gaussian Splatting (3DGS) in Visual Simultaneous Localization and Mapping (VS-LAM) 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-frommotion methods, significantly shortens the training time needed to achieve high-quality renders. I. INTRODUCTION Visual Simultaneous Localization and Mapping (VSLAM) fixed set of poses and initial points from a structure-frommotion is crucial for developing robust mobile robotics. After converting the VSLAM system would reconstruct environments with photorealistic initial points into 3D Gaussians, their positions, sizes, and accuracy from live video input.