SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM
This work addresses performance and quality issues in RGBD SLAM for robotics and AR/VR applications, presenting an incremental improvement over existing 3D Gaussian Splatting methods.
The paper tackles the problem of slow convergence and limited rendering quality in RGBD SLAM by using pixel-aligned Gaussians that adjust depth positions to improve radiance fields, achieving advantages in rendering, tracking, runtime, and storage over latest methods.
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 .