Splat-SLAM: Globally Optimized RGB-Only SLAM with 3D Gaussians
Abstract
3D Gaussian Splatting offers a compact, efficient approach to RGB-only dense SLAM by providing high-quality map rendering with a dense, optimized 3D Gaussian map. Existing methods, however, often underperform in reconstruction quality compared to alternatives like neural point clouds, primarily due to limited map and pose optimization or reliance on monocular depth. We introduce the first RGB-only SLAM system with globally optimized tracking, dynamically adapting the Gaussian map to keyframe pose and depth updates. To address the lack of geometric priors, we incorporate so called Disparity, Scale and Pose Optimization (DSPO) for bundle adjustment, jointly optimizing pose, depth, and monocular depth scale. Our tests on Replica, TUM-RGBD, and ScanNet confirm this approach achieves superior or comparable tracking, mapping, and rendering accuracy with small map sizes and fast runtimes.
Cite
Text
Sandström et al. "Splat-SLAM: Globally Optimized RGB-Only SLAM with 3D Gaussians." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.Markdown
[Sandström et al. "Splat-SLAM: Globally Optimized RGB-Only SLAM with 3D Gaussians." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.](https://mlanthology.org/cvprw/2025/sandstrom2025cvprw-splatslam/)BibTeX
@inproceedings{sandstrom2025cvprw-splatslam,
title = {{Splat-SLAM: Globally Optimized RGB-Only SLAM with 3D Gaussians}},
author = {Sandström, Erik and Zhang, Ganlin and Tateno, Keisuke and Oechsle, Michael and Niemeyer, Michael and Zhang, Youmin and Patel, Manthan and Van Gool, Luc and Oswald, Martin R. and Tombari, Federico},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2025},
pages = {1680-1691},
url = {https://mlanthology.org/cvprw/2025/sandstrom2025cvprw-splatslam/}
}