Abstract. In this paper, we propose the 3DFeat-Net which learns both
3D feature detector and descriptor for point cloud matching using weak
supervision. Unlike many existing works, we do not require manual annotation of matching point clusters. Instead, we leverage on alignment and
attention mechanisms to learn feature correspondences from GPS/INS
tagged 3D point clouds without explicitly specifying them. We create
training and benchmark outdoor Lidar datasets, and experiments show
that 3DFeat-Net obtains state-of-the-art performance on these gravityaligned datasets