PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors

Abstract

We present PPF-FoldNet for unsupervised learning of 3D local descriptors on pure point cloud geometry. Based on the folding-based auto-encoding of well known point pair features, PPF-FoldNet offers many desirable properties: it necessitates neither supervision, nor a sensitive local reference frame, benefits from point-set sparsity, is end-to-end, fast, and can extract powerful rotation invariant descriptors. Thanks to a novel feature visualization, its evolution can be monitored to provide interpretable insights. Our extensive experiments demonstrate that despite having six degree-of-freedom invariance and lack of training labels, our network achieves state of the art results in standard benchmark datasets and outperforms its competitors when rotations and varying point densities are present. PPF-FoldNet achieves $9\%$ higher recall on standard benchmarks, $23\%$ higher recall when rotations are introduced into the same datasets and finally, a margin of $>35\%$ is attained when point density is significantly decreased.

arXiv commentAccepted for publication at ECCV 2018

References in corpus (6)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Learning Representations and Generative Models for 3D Point Clouds
• Dynamic Graph Convolutional Networks
• LIFT: Learned Invariant Feature Transform
• PU-Net: Point Cloud Upsampling Network

Cited by in corpus (5)

• Patch-based Progressive 3D Point Set Upsampling
• PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval
• USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds
• Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers
• Adversarial shape perturbations on 3D point clouds