Calib-Anything: Zero-training LiDAR-Camera Extrinsic Calibration Method Using Segment Anything
This addresses the need for automatic and generic calibration in robotics and autonomous systems, though it is incremental as it builds on existing foundation models.
The authors tackled the problem of extrinsic calibration between LiDAR and cameras by proposing a zero-training method using the Segment Anything Model (SAM) to adapt to common scenes without additional training, achieving comparable accuracy across different datasets.
The research on extrinsic calibration between Light Detection and Ranging(LiDAR) and camera are being promoted to a more accurate, automatic and generic manner. Since deep learning has been employed in calibration, the restrictions on the scene are greatly reduced. However, data driven method has the drawback of low transfer-ability. It cannot adapt to dataset variations unless additional training is taken. With the advent of foundation model, this problem can be significantly mitigated. By using the Segment Anything Model(SAM), we propose a novel LiDAR-camera calibration method, which requires zero extra training and adapts to common scenes. With an initial guess, we opimize the extrinsic parameter by maximizing the consistency of points that are projected inside each image mask. The consistency includes three properties of the point cloud: the intensity, normal vector and categories derived from some segmentation methods. The experiments on different dataset have demonstrated the generality and comparable accuracy of our method. The code is available at https://github.com/OpenCalib/CalibAnything.