Graphite: GRAPH-Induced feaTure Extraction for Point Cloud Registration

TL;DR

Graphite introduces a graph neural network-based feature extraction and keypoint detection method for 3D point clouds, improving registration accuracy while maintaining efficiency, suitable for large and sparse datasets.

Contribution

The paper presents a novel graph neural network approach for robust feature extraction and keypoint detection in 3D point clouds, enhancing registration performance.

Findings

Achieves comparable registration results to state-of-the-art methods.

Detects keypoints and extracts descriptors in ~0.018 seconds for 100 patches.

Improves robustness and efficiency in processing large, sparse point clouds.

Abstract

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.