Event
Targetless Joint Calibration of Camera Intrinsics and LiDAR Extrinsics
1 reports · 1 sources
Simon Bultmann and co-authors propose a fully automatic, targetless calibration framework that jointly estimates camera intrinsics, radial-tangential distortion, and camera-LiDAR extrinsics from raw images and LiDAR scans. The authors state that the method, through intrinsics- and distortion-aware correspondence learning, extends calibration based on dense pixel correspondences from rectified images to raw cameras, and iteratively couples correspondence prediction with nonlinear optimization during calibration. Zero-shot evaluations on unseen KITTI configurations and three real robotic platforms show that the joint calibration improves extrinsic accuracy while recovering accurate intrinsics.
Report timeline
- Target-free joint camera-LiDAR intrinsic and extrinsic calibration method
The authors propose a fully automatic, target-free framework that jointly estimates camera intrinsics, radial-tangential distortion, and camera-LiDAR extrinsics from raw images and LiDAR scans. The method extends deep pixel-point correspondence-based calibration from rectified images to raw cameras through intrinsic- and distortion-aware correspondence learning, and iteratively couples correspondence prediction with nonlinear optimization during calibration. Zero-shot evaluations on an unseen KITTI configuration and on three real robotic platforms show that joint calibration improves extrinsic accuracy while recovering accurate intrinsics.
arXiv cs.RO ·