GAFAR revisited—Exploring the limits of point cloud registration on sparse subsets

Robust estimation of a rigid transformation aligning two point clouds is a fundamental building block in many tasks in computer vision and robotics, such as mapping, (re-)localization, SLAM or 3D scanning, and many more. Deep-Learning based registration methods have proven superior in terms of robustness to outliers and bad initializations, yet their resource needs often render them unsuitable for applications where space, energy and real-time constraints come into play. Since - provided a good initialization - conventional registration algorithms like ICP prove to be fast and accurate, we may relax the requirements of absolute precision of a learning-based matcher and instead focus our attention on efficiency, robustness and generalization. In prior work, we introduced our small, fast and light-weight registration algorithm GAFAR, which works on sparse subsets of point clouds and exhibits a small enough footprint to be deployed on edge devices in mobile applications, while still providing accurate results and promising generalization ability. Based thereon, we develop this idea further towards applicability on real world data with improvements to the algorithm as well as further evaluations and analyses. We showcase this by applying it to Kitti Odometry Benchmark and 3DMatch dataset as well as demonstrating its usability on edge devices. The code and trained weights are published in https://github.com/mordecaimalignatius/GAFAR/ . • Fast and lightweight deep-learning based point cloud registration algorithm working on very sparse subsets, small enough to be deployed on edge devices. • We showcase its performance on point clouds from LiDAR scanners and ToF cameras, as well as its deployability on edge devices. • We introduce several improvements of the architecture, resulting in generally higher precision and better recall.