Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces an extrinsic-aware cross-attention mechanism for camera-LiDAR extrinsic calibration, directly aligning image patches and LiDAR point groups in their native domains. By injecting extrinsic parameter hypotheses into the attention mechanism, the method avoids the geometric distortions introduced by projecting LiDAR points into depth maps. Experiments on KITTI and nuScenes show the approach significantly outperforms existing methods, achieving accurate calibration in 88% and 99% of cases respectively under large extrinsic perturbations.
Projecting LiDAR data into 2D depth maps hurts camera-LiDAR calibration, but this new cross-attention method operating in native domains achieves state-of-the-art accuracy, especially under large initial misalignments.
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 aligns image patches and LiDAR point groups in their native domains. The proposed attention mechanism explicitly injects extrinsic parameter hypotheses into the correspondence modeling process, enabling geometry-consistent cross-modal interaction without relying on projected 2D depth maps. Extensive experiments on the KITTI and nuScenes benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches in both accuracy and robustness. Under large extrinsic perturbations, our approach achieves accurate calibration in 88% of KITTI cases and 99% of nuScenes cases, substantially surpassing the second-best baseline. We have open sourced our code on https://github.com/gitouni/ProjFusion to benefit the community.