Towards Real-Time Gaussian Splatting: Accelerating 3DGS through Photometric SLAM
This addresses the challenge of achieving real-time, high-quality 3D reconstructions in SLAM systems for applications like robotics or AR, though it appears incremental as it builds on existing methods.
The paper tackles the problem of slow training and reduced tracking performance when integrating 3D Gaussian Splatting (3DGS) with Visual SLAM, by proposing to combine 3DGS with Direct Sparse Odometry, which significantly shortens training time to enable real-time operation on mobile hardware.
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.