CMRNet: Camera to LiDAR-Map Registration
This addresses camera-to-LiDAR registration for autonomous vehicles, presenting a novel method but with incremental improvements in accuracy.
The paper tackles the problem of localizing an RGB image in a LiDAR map using a CNN-based approach, achieving 0.27m and 1.07deg median accuracy on the KITTI dataset without prior map training.
In this paper we present CMRNet, a realtime approach based on a Convolutional Neural Network to localize an RGB image of a scene in a map built from LiDAR data. Our network is not trained in the working area, i.e. CMRNet does not learn the map. Instead it learns to match an image to the map. We validate our approach on the KITTI dataset, processing each frame independently without any tracking procedure. CMRNet achieves 0.27m and 1.07deg median localization accuracy on the sequence 00 of the odometry dataset, starting from a rough pose estimate displaced up to 3.5m and 17deg. To the best of our knowledge this is the first CNN-based approach that learns to match images from a monocular camera to a given, preexisting 3D LiDAR-map.