PPFNet: Global Context Aware Local Features for Robust 3D Point Matching

TL;DR

PPFNet introduces a globally informed local feature descriptor for 3D point cloud matching, leveraging point-pair features and a permutation-invariant network to improve robustness and recall in unorganized data.

Contribution

The paper presents PPFNet, a novel deep learning architecture that incorporates global context into local 3D descriptors using point-pair features and a permutation-invariant design.

Findings

Increased recall and robustness in 3D point matching

Improved invariance to unorganized point clouds

Effective exploitation of raw point cloud sparsity

Abstract

We present PPFNet - Point Pair Feature NETwork for deeply learning a globally informed 3D local feature descriptor to find correspondences in unorganized point clouds. PPFNet learns local descriptors on pure geometry and is highly aware of the global context, an important cue in deep learning. Our 3D representation is computed as a collection of point-pair-features combined with the points and normals within a local vicinity. Our permutation invariant network design is inspired by PointNet and sets PPFNet to be ordering-free. As opposed to voxelization, our method is able to consume raw point clouds to exploit the full sparsity. PPFNet uses a novel $\textit{N-tuple}$ loss and architecture injecting the global information naturally into the local descriptor. It shows that context awareness also boosts the local feature representation. Qualitative and quantitative evaluations of our network suggest increased recall, improved robustness and invariance as well as a vital step in the 3D descriptor extraction performance.