A successful point cloud registration often lies on robust establishment of
sparse matches through discriminative 3D local features. Despite the fast
evolution of learning-based 3D feature descriptors, little attention has been
drawn to the learning of 3D feature detectors, even less for a joint learning
of the two tasks. In this paper, we leverage a 3D fully convolutional network
for 3D point clouds, and propose a novel and practical learning mechanism that
densely predicts both a detection score and a description feature for each 3D
point. In particular, we propose a keypoint selection strategy that overcomes
the inherent density variations of 3D point clouds, and further propose a
self-supervised detector loss guided by the on-the-fly feature matching results
during training. Finally, our method achieves state-of-the-art results in both
indoor and outdoor scenarios, evaluated on 3DMatch and KITTI datasets, and
shows its strong generalization ability on the ETH dataset. Towards practical
use, we show that by adopting a reliable feature detector, sampling a smaller
number of features is sufficient to achieve accurate and fast point cloud
alignment.[code release](this https URL)

本文提出了一种新型实用的学习机制，利用三维全卷积网络，旨在稠密地预测每个三维点的检测分数和描述特征，并通过自监督的检测器损失，在训练过程中指导即兴的特征匹配结果。最后，我们的方法在 3DMatch 和 KITTI 数据集的室内和室外场景中，均取得了最先进的结果，并在 ETH 数据集上展现了其强大的概括能力，为实现准确快速的点云对其，提出了一种可靠的特征检测器。