Enables precise Camera-LiDAR extrinsic calibration even under massive initial misalignments that typically break automated calibration systems.
April 1, 2026
Original Paper
Native-Domain Cross-Attention for Camera-LiDAR Extrinsic Calibration Under Large Initial Perturbations
arXiv · 2603.29414
The Takeaway
Establishing sensor correspondence usually requires a very close initial estimate. By using a native-domain cross-attention framework instead of 2D projections, this method allows for fully automated, robust sensor recalibration in the field for autonomous vehicles.
From the abstract
Accurate camera-LiDAR fusion relies on precise extrinsic calibration, which fundamentally depends on establishing reliable cross-modal correspondences under potentially large misalignments. Existing learning-based methods typically project LiDAR points into depth maps for feature fusion, which distorts 3D geometry and degrades performance when the extrinsic initialization is far from the ground truth. To address this issue, we propose an extrinsic-aware cross-attention framework that directly al