# CMRNet: Camera to LiDAR-Map Registration

## TL;DR

CMRNet is a real-time CNN-based method that localizes RGB images within a preexisting LiDAR map without prior training in the specific area, demonstrating high accuracy on the KITTI dataset.

## Contribution

This paper introduces CMRNet, the first CNN approach to match monocular camera images to a preexisting LiDAR map for localization.

## Key findings

- Achieves 0.27m median localization accuracy on KITTI sequence 00.
- Operates without training in the specific working area.
- Processes each frame independently without tracking.

## Abstract

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.