Deep Learning for 3D Keypoint Detection in Large-Scale Point Cloud Registration

The main solution for large-scale point clouds registration is to first obtain a set of matched 3D keypoint pairs and then accomplish the point cloud registration task based on these matched keypoint pairs. However, at present, many methods study the feature descriptors in the point clouds registration task, but few methods discuss the 3D keypoints detection issues. The commonly used 3D keypoints detection strategy is the voxel-grid-based downsampling method, and the detected 3D keypoints are usually with a relatively huge amount and also with no explicit geometrical properties, which finally leads to a low inlier ratio. In this study, we rethink the 3D keypoints detection problem for large-scale point clouds with deep learning. Specifically, we discuss four kinds of 3D keypoints detection methods based on the joint keypoint detection and description learning framework D3Feat, and carry out extensive analyses on both the indoor large-scale point clouds dataset 3DMatch and the outdoor large-scale point clouds dataset KITTI Odometry. Experimental results demonstrate that the Multi-layer Perceptron (MLP) based method achieves the best inlier ratios under the different numbers of extracted 3D keypoints on both the indoor and outdoor large-scale point clouds. Further, we test these four kinds of keypoints detection methods under the application of large-scale point clouds registration, and the MLP-based method also achieves the state-of-the-art registration performance. In summary, this study proposes a deep learning-based approach to address the 3D keypoints detection problem for large-scale point clouds registration. The proposed methods outperform the traditional voxel-grid-based downsampling method in terms of the inlier ratio and registration performance. This study sheds light on the importance of 3D keypoints detection in large-scale point clouds registration and provides a promising direction for future research.