<ul><li>SaliencyI2PLoc is a contrastive learning based architecture for image to point cloud global localization.</li><li>It addresses the modality gap between images and point clouds and maintains feature alignment and relation consistency.</li><li>Saliency map is fused into feature aggregation for more representative global features.</li><li>Experiments show significant improvement in cross-modality global localization compared to baseline methods.</li></ul>

SaliencyI2PLoc: saliency-guided image-point cloud localization using contrastive learning

Discover more