Rad-GS: Radar-Vision Integration for 3D Gaussian Splatting SLAM in Outdoor Environments

TL;DR

Rad-GS is a novel radar-vision SLAM system that uses 3D Gaussian representations to enable accurate, large-scale outdoor mapping and scene reconstruction by integrating radar and camera data.

Contribution

Rad-GS introduces a 4D radar-camera SLAM framework with a differentiable 3D Gaussian representation, improving outdoor localization and large-scale scene reconstruction.

Findings

Achieves localization accuracy comparable to camera or LiDAR-based methods.

Effectively suppresses noise and reduces memory in large-scale environments.

Demonstrates successful kilometer-scale outdoor scene reconstruction.

Abstract

We present Rad-GS, a 4D radar-camera SLAM system designed for kilometer-scale outdoor environments, utilizing 3D Gaussian as a differentiable spatial representation. Rad-GS combines the advantages of raw radar point cloud with Doppler information and geometrically enhanced point cloud to guide dynamic object masking in synchronized images, thereby alleviating rendering artifacts and improving localization accuracy. Additionally, unsynchronized image frames are leveraged to globally refine the 3D Gaussian representation, enhancing texture consistency and novel view synthesis fidelity. Furthermore, the global octree structure coupled with a targeted Gaussian primitive management strategy further suppresses noise and significantly reduces memory consumption in large-scale environments. Extensive experiments and ablation studies demonstrate that Rad-GS achieves performance comparable to traditional 3D Gaussian methods based on camera or LiDAR inputs, highlighting the feasibility of robust outdoor mapping using 4D mmWave radar. Real-world reconstruction at kilometer scale validates the potential of Rad-GS for large-scale scene reconstruction.