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

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 $\text{N-tuple}$ 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.

Accepted for publication at CVPR 2018

References in corpus (8)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Semi-Supervised Classification with Graph Convolutional Networks
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• 3D ShapeNets: A Deep Representation for Volumetric Shapes
• 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
• Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images
• Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation
• Geometric features for voxel-based surface recognition

Cited by in corpus (9)

• 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
• BodyNet: Volumetric Inference of 3D Human Body Shapes
• 3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image
• AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects
• Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
• Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration
• MG-SAGC: A multiscale graph and its self-adaptive graph convolution network for 3D point clouds
• Plane Pair Matching for Efficient 3D View Registration
• Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits