Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Large-Scale Gaussian Splatting SLAM

Zhe Xin, Chenyang Wu, Penghui Huang, Yanyong Zhang, Yinian Mao, Guoquan Huang

TL;DR

This paper introduces a large-scale 3DGS-based visual SLAM with stereo cameras, termed LSG-SLAM, which achieves superior performance over existing Neural, 3DGS-based, and even traditional approaches.

Abstract

The recently developed Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown encouraging and impressive results for visual SLAM. However, most representative methods require RGBD sensors and are only available for indoor environments. The robustness of reconstruction in large-scale outdoor scenarios remains unexplored. This paper introduces a large-scale 3DGS-based visual SLAM with stereo cameras, termed LSG-SLAM. The proposed LSG-SLAM employs a multi-modality strategy to estimate prior poses under large view changes. In tracking, we introduce feature-alignment warping constraints to alleviate the adverse effects of appearance similarity in rendering losses. For the scalability of large-scale scenarios, we introduce continuous Gaussian Splatting submaps to tackle unbounded scenes with limited memory. Loops are detected between GS submaps by place recognition and the relative pose between looped keyframes is optimized utilizing rendering and feature warping losses. After the global optimization of camera poses and Gaussian points, a structure refinement module enhances the reconstruction quality. With extensive evaluations on the EuRoc and KITTI datasets, LSG-SLAM achieves superior performance over existing Neural, 3DGS-based, and even traditional approaches. Project page: https://lsg-slam.github.io.

Large-Scale Gaussian Splatting SLAM

TL;DR

This paper introduces a large-scale 3DGS-based visual SLAM with stereo cameras, termed LSG-SLAM, which achieves superior performance over existing Neural, 3DGS-based, and even traditional approaches.

Abstract

The recently developed Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown encouraging and impressive results for visual SLAM. However, most representative methods require RGBD sensors and are only available for indoor environments. The robustness of reconstruction in large-scale outdoor scenarios remains unexplored. This paper introduces a large-scale 3DGS-based visual SLAM with stereo cameras, termed LSG-SLAM. The proposed LSG-SLAM employs a multi-modality strategy to estimate prior poses under large view changes. In tracking, we introduce feature-alignment warping constraints to alleviate the adverse effects of appearance similarity in rendering losses. For the scalability of large-scale scenarios, we introduce continuous Gaussian Splatting submaps to tackle unbounded scenes with limited memory. Loops are detected between GS submaps by place recognition and the relative pose between looped keyframes is optimized utilizing rendering and feature warping losses. After the global optimization of camera poses and Gaussian points, a structure refinement module enhances the reconstruction quality. With extensive evaluations on the EuRoc and KITTI datasets, LSG-SLAM achieves superior performance over existing Neural, 3DGS-based, and even traditional approaches. Project page: https://lsg-slam.github.io.
Paper Structure (14 sections, 7 equations, 2 figures, 7 tables)

This paper contains 14 sections, 7 equations, 2 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. LSG-SLAM
  4. 3DGS Map Representation
  5. Tracking
  6. Mapping
  7. Loop Closure
  8. GS Refinement
  9. Experimental Results
  10. Evaluation on EuRoC
  11. Evaluation on KITTI
  12. Ablation Study
  13. Efficiency Analysis
  14. Conclusions and Future Work

Figures (2)

  • Figure 1: Results on KITTI sequence 00. LSG-SLAM enables precise camera tracking and high-fidelity reconstruction in challenging large-scale scenarios. We showcase the trajectory error before and after loop closure and some sample keyframes with associated submaps. The PSNR is evaluated after the structure refinement.
  • Figure 2: The overview of LSG-SLAM. For each incoming frame, we employ the multi-modality prior pose estimation strategy and subsequently utilize rendering loss and feature warping loss to optimize the current pose. Selected keyframes are then employed to refine the scene and add more Gaussian points. Incorporating loop detection and loop constraint estimation utilizing GS submaps, all keyframe poses are optimized. Subsequently, all Gaussian points are adjusted based on the relative transformation of their associated keyframes. After optimizing the pose of all images, a structure refinement process is executed to enhance the reconstruction quality for novel view synthesis.