GS-GVINS: A Tightly-integrated GNSS-Visual-Inertial Navigation System Augmented by 3D Gaussian Splatting

2025-02-16

AI Summary

To address the insufficient robustness and accuracy of GNSS-visual-inertial navigation systems (GNSS-VINS) in large-scale outdoor environments, this paper proposes the first tightly coupled GNSS-VINS framework leveraging 3D Gaussian Splatting (3DGS) as a continuous, differentiable geometric representation of outdoor scenes. Our key contributions are: (1) the first integration of 3DGS into GNSS-VINS with analytical Jacobians of SE(3) camera poses, enabling end-to-end differentiable optimization; (2) a motion-aware 3D Gaussian pruning mechanism to maintain real-time rendering quality under dynamic conditions; and (3) a tightly coupled nonlinear optimization that fuses multi-source measurements (GNSS pseudoranges, carrier phases, visual features, and IMU pre-integration), combined with motion-adaptive map updating. Evaluated across open-field, suburban, and urban driving scenarios, our method significantly improves localization accuracy and generalization—demonstrating strong cross-scenario transferability on both self-collected and public datasets.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: 3D Computer Vision
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Recently, the emergence of 3D Gaussian Splatting (3DGS) has drawn significant attention in the area of 3D map reconstruction and visual SLAM. While extensive research has explored 3DGS for indoor trajectory tracking using visual sensor alone or in combination with Light Detection and Ranging (LiDAR) and Inertial Measurement Unit (IMU), its integration with GNSS for large-scale outdoor navigation remains underexplored. To address these concerns, we proposed GS-GVINS: a tightly-integrated GNSS-Visual-Inertial Navigation System augmented by 3DGS. This system leverages 3D Gaussian as a continuous differentiable scene representation in largescale outdoor environments, enhancing navigation performance through the constructed 3D Gaussian map. Notably, GS-GVINS is the first GNSS-Visual-Inertial navigation application that directly utilizes the analytical jacobians of SE3 camera pose with respect to 3D Gaussians. To maintain the quality of 3DGS rendering in extreme dynamic states, we introduce a motionaware 3D Gaussian pruning mechanism, updating the map based on relative pose translation and the accumulated opacity along the camera ray. For validation, we test our system under different driving environments: open-sky, sub-urban, and urban. Both self-collected and public datasets are used for evaluation. The results demonstrate the effectiveness of GS-GVINS in enhancing navigation accuracy across diverse driving environments.

Problem

• Integrates GNSS with 3D Gaussian Splatting for outdoor navigation.
• Enhances navigation accuracy using 3D Gaussian maps.
• Introduces motion-aware pruning for dynamic state rendering.

Innovation

• Integrates GNSS with 3D Gaussian Splatting
• Utilizes SE3 camera pose jacobians
• Implements motion-aware 3D Gaussian pruning