3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration

ECCV 2018  ·  Zi Jian Yew, Gim Hee Lee ·

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 gravity-aligned datasets.

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Point Cloud Registration KITTI 3DFeat-Net Success Rate 95.97 # 6

Methods


No methods listed for this paper. Add relevant methods here