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

08/30/2018
by   Haowen Deng, et al.
0

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.

READ FULL TEXT
research
09/27/2022

RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration

Successful point cloud registration relies on accurate correspondences e...
research
05/21/2021

Generalisable and distinctive 3D local deep descriptors for point cloud registration

An effective 3D descriptor should be invariant to different geometric tr...
research
03/14/2023

Rotation-Invariant Transformer for Point Cloud Matching

The intrinsic rotation invariance lies at the core of matching point clo...
research
09/01/2021

You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors

In this paper, we propose a novel local descriptor-based framework, call...
research
11/24/2020

SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration

Extracting robust and general 3D local features is key to downstream tas...
research
11/16/2018

The Perfect Match: 3D Point Cloud Matching with Smoothed Densities

We propose 3DSmoothNet, a full workflow to match 3D point clouds with a ...
research
12/23/2019

Geometry Sharing Network for 3D Point Cloud Classification and Segmentation

In spite of the recent progresses on classifying 3D point cloud with dee...

Please sign up or login with your details

Forgot password? Click here to reset