Log In Sign Up

Graphite: GRAPH-Induced feaTure Extraction for Point Cloud Registration

by   Mahdi Saleh, et al.

3D Point clouds are a rich source of information that enjoy growing popularity in the vision community. However, due to the sparsity of their representation, learning models based on large point clouds is still a challenge. In this work, we introduce Graphite, a GRAPH-Induced feaTure Extraction pipeline, a simple yet powerful feature transform and keypoint detector. Graphite enables intensive down-sampling of point clouds with keypoint detection accompanied by a descriptor. We construct a generic graph-based learning scheme to describe point cloud regions and extract salient points. To this end, we take advantage of 6D pose information and metric learning to learn robust descriptions and keypoints across different scans. We Reformulate the 3D keypoint pipeline with graph neural networks which allow efficient processing of the point set while boosting its descriptive power which ultimately results in more accurate 3D registrations. We demonstrate our lightweight descriptor on common 3D descriptor matching and point cloud registration benchmarks and achieve comparable results with the state of the art. Describing 100 patches of a point cloud and detecting their keypoints takes only  0.018 seconds with our proposed network.


page 4

page 7

page 15

page 16


SKD: Unsupervised Keypoint Detecting for Point Clouds using Embedded Saliency Estimation

In this work we present a novel keypoint detector that uses saliency to ...

UPDesc: Unsupervised Point Descriptor Learning for Robust Registration

In this work, we propose UPDesc, an unsupervised method to learn point d...

Semantic keypoint extraction for scanned animals using multi-depth-camera systems

Keypoint annotation in point clouds is an important task for 3D reconstr...

Learning a 3D descriptor for cross-source point cloud registration from synthetic data

As the development of 3D sensors, registration of 3D data (e.g. point cl...

LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloud

Feature extraction and matching are the basic parts of many computer vis...

Learning Dense Features for Point Cloud Registration Using Graph Attention Network

Point cloud registration is a fundamental task in many applications such...