SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM

TL;DR

This paper introduces SGAD-SLAM, a novel RGBD SLAM method that uses adjustable pixel-aligned Gaussians for improved rendering and tracking efficiency, outperforming existing approaches in quality and speed.

Contribution

It proposes a new Gaussian representation with adjustable positions and depth modeling for enhanced SLAM performance and scalability.

Findings

Improved rendering quality over state-of-the-art methods

Faster camera tracking with Gaussian depth distributions

Reduced runtime and storage complexity

Abstract

3D Gaussian Splatting (3DGS) has made remarkable progress in RGBD SLAM. Current methods usually use 3D Gaussians or view-tied 3D Gaussians to represent radiance fields in tracking and mapping. However, these Gaussians are either too flexible or too limited in movements, resulting in slow convergence or limited rendering quality. To resolve this issue, we adopt pixel-aligned Gaussians but allow each Gaussian to adjust its position along its ray to maximize the rendering quality, even if Gaussians are simplified to improve system scalability. To speed up the tracking, we model the depth distribution around each pixel as a Gaussian distribution, and then use these distributions to align each frame to the 3D scene quickly. We report our evaluations on widely used benchmarks, justify our designs, and show advantages over the latest methods in view rendering, camera tracking, runtime, and storage complexity. Please see our project page for code and videos at https://machineperceptionlab.github.io/SGAD-SLAM-Project .