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

by   Zan Gojcic, et al.

We propose 3DSmoothNet, a full workflow to match 3D point clouds with a siamese deep learning architecture and fully convolutional layers using a voxelized smoothed density value (SDV) representation. The latter is computed per interest point and aligned to the local reference frame (LRF) to achieve rotation invariance. Our compact, learned, rotation invariant 3D point cloud descriptor achieves 94.9 outperforming the state-of-the-art by more than 20 percent points with only 32 output dimensions. This very low output dimension allows for near real-time correspondence search with 0.1 ms per feature point on a standard PC. Our approach is sensor- and scene-agnostic because of SDV, LRF and learning highly descriptive features with fully convolutional layers. We show that 3DSmoothNet trained only on RGB-D indoor scenes of buildings achieves 79.0 on laser scans of outdoor vegetation, more than double the performance of our closest, learningbased competitors.


page 3

page 4

page 5

page 6


Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks

Point cloud analysis is an area of increasing interest due to the develo...

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

An effective 3D descriptor should be invariant to different geometric tr...

Distinctive 3D local deep descriptors

We present a simple but yet effective method for learning distinctive 3D...

Learning Graph-Convolutional Representations for Point Cloud Denoising

Point clouds are an increasingly relevant data type but they are often c...

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

In this paper, we propose a novel local descriptor-based framework, call...

Learning Local Displacements for Point Cloud Completion

We propose a novel approach aimed at object and semantic scene completio...

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

We present PPF-FoldNet for unsupervised learning of 3D local descriptors...

Code Repositories


[CVPR2019] The Perfect Match: 3D Point Cloud Matching with Smoothed Densities

view repo


Что я делаю с проектом Innav

view repo

Please sign up or login with your details

Forgot password? Click here to reset