Rad-GS: Radar-Vision Integration for 3D Gaussian Splatting SLAM in Outdoor Environments
This work addresses outdoor mapping for autonomous systems by combining radar and vision, though it is incremental as it adapts existing 3D Gaussian methods to new sensor inputs.
The paper tackled the problem of robust outdoor SLAM in large-scale environments by integrating 4D radar and camera data with 3D Gaussian splatting, achieving performance comparable to camera- or LiDAR-based methods and enabling kilometer-scale reconstruction.
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.