GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels
This work addresses geometry inconsistencies in dense RGB-D SLAM for robotics and AR/VR applications, representing an incremental improvement over existing Gaussian-based methods.
The paper tackles geometry distortion in Gaussian-based SLAM systems by proposing a 2D Gaussian incremental reconstruction strategy and Surface-aware Depth Rendering, resulting in improved tracking precision and rendering fidelity as demonstrated in experiments across multiple datasets.
We propose GauS-SLAM, a dense RGB-D SLAM system that leverages 2D Gaussian surfels to achieve robust tracking and high-fidelity mapping. Our investigations reveal that Gaussian-based scene representations exhibit geometry distortion under novel viewpoints, which significantly degrades the accuracy of Gaussian-based tracking methods. These geometry inconsistencies arise primarily from the depth modeling of Gaussian primitives and the mutual interference between surfaces during the depth blending. To address these, we propose a 2D Gaussian-based incremental reconstruction strategy coupled with a Surface-aware Depth Rendering mechanism, which significantly enhances geometry accuracy and multi-view consistency. Additionally, the proposed local map design dynamically isolates visible surfaces during tracking, mitigating misalignment caused by occluded regions in global maps while maintaining computational efficiency with increasing Gaussian density. Extensive experiments across multiple datasets demonstrate that GauS-SLAM outperforms comparable methods, delivering superior tracking precision and rendering fidelity. The project page will be made available at https://gaus-slam.github.io.