Learning Compact Geometric Features

ICCV 2017  ·  Marc Khoury, Qian-Yi Zhou, Vladlen Koltun ·

We present an approach to learning features that represent the local geometry around a point in an unstructured point cloud. Such features play a central role in geometric registration, which supports diverse applications in robotics and 3D vision. Current state-of-the-art local features for unstructured point clouds have been manually crafted and none combines the desirable properties of precision, compactness, and robustness. We show that features with these properties can be learned from data, by optimizing deep networks that map high-dimensional histograms into low-dimensional Euclidean spaces. The presented approach yields a family of features, parameterized by dimension, that are both more compact and more accurate than existing descriptors.

PDF Abstract ICCV 2017 PDF ICCV 2017 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Point Cloud Registration ETH (trained on 3DMatch) CGF Recall 0.202 # 9

Methods


No methods listed for this paper. Add relevant methods here