A Novel LiDAR–Camera Joint Calibration Network Based on Cross-Modal Feature Fusion

In autonomous driving and robotic navigation, the fusion of multimodal data from LiDAR and cameras relies on accurate extrinsic calibration. However, the calibration accuracy may drop when there is external disturbance such as sensor vibrations, temperature fluctuations, and aging. To address this problem, this paper presents a novel LiDAR-camera joint calibration network based on CMAF (cross-modal attention fusion) and CDFE (cross-domain feature extraction). The CMAF module is constructed based on region-level matching and pixel-level interaction to improve the cross-modal feature alignment and fusion. To address the semantic inconsistency between encoder and decoder features, the CDFE is designed for U-shaped architecture with multimodal skip connections to capture large-scale contextual correlations through the transformation from spatial domain to frequency domain, and it can maintain semantic consistency through the fusion of global features and original features (residual information) based on the dual-path architecture. Experiments on the KITTI Odometry dataset and KITTI-360 dataset show that our network not only significantly outperforms mainstream methods and demonstrates strong generalization capabilities but also achieves high computational efficiency.