Robust LiDAR-Camera Calibration with 2D Gaussian Splatting
This addresses the calibration challenge for robotics applications by eliminating the need for auxiliary targets, though it is an incremental improvement over existing targetless methods.
The paper tackles the problem of LiDAR-camera calibration by proposing a targetless method that uses 2D Gaussian Splatting to reconstruct geometry from LiDAR point clouds and optimize extrinsic parameters through photometric, reprojection, and triangulation losses, resulting in enhanced robustness and accuracy.
LiDAR-camera systems have become increasingly popular in robotics recently. A critical and initial step in integrating the LiDAR and camera data is the calibration of the LiDAR-camera system. Most existing calibration methods rely on auxiliary target objects, which often involve complex manual operations, whereas targetless methods have yet to achieve practical effectiveness. Recognizing that 2D Gaussian Splatting (2DGS) can reconstruct geometric information from camera image sequences, we propose a calibration method that estimates LiDAR-camera extrinsic parameters using geometric constraints. The proposed method begins by reconstructing colorless 2DGS using LiDAR point clouds. Subsequently, we update the colors of the Gaussian splats by minimizing the photometric loss. The extrinsic parameters are optimized during this process. Additionally, we address the limitations of the photometric loss by incorporating the reprojection and triangulation losses, thereby enhancing the calibration robustness and accuracy.