UPDesc: Unsupervised Point Descriptor Learning for Robust Registration

08/05/2021
by   Lei Li, et al.
0

In this work, we propose UPDesc, an unsupervised method to learn point descriptors for robust point cloud registration. Our work builds upon a recent supervised 3D CNN-based descriptor extraction framework, namely, 3DSmoothNet, which leverages a voxel-based representation to parameterize the surrounding geometry of interest points. Instead of using a predefined fixed-size local support in voxelization, which potentially limits the access of richer local geometry information, we propose to learn the support size in a data-driven manner. To this end, we design a differentiable voxelization module that can back-propagate gradients to the support size optimization. To optimize descriptor similarity, the prior 3D CNN work and other supervised methods require abundant correspondence labels or pose annotations of point clouds for crafting metric learning losses. Differently, we show that unsupervised learning of descriptor similarity can be achieved by performing geometric registration in networks. Our learning objectives consider descriptor similarity both across and within point clouds without supervision. Through extensive experiments on point cloud registration benchmarks, we show that our learned descriptors yield superior performance over existing unsupervised methods.

READ FULL TEXT

page 1

page 4

page 8

research
07/17/2020

DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization

For relocalization in large-scale point clouds, we propose the first app...
research
11/18/2021

IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration

The existing state-of-the-art point descriptor relies on structure infor...
research
07/18/2023

SphereNet: Learning a Noise-Robust and General Descriptor for Point Cloud Registration

Point cloud registration is to estimate a transformation to align point ...
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
08/26/2021

A Robust Loss for Point Cloud Registration

The performance of surface registration relies heavily on the metric use...
research
10/17/2017

Deep Spectral Descriptors: Learning the point-wise correspondence metric via Siamese deep neural networks

A robust and informative local shape descriptor plays an important role ...
research
01/15/2018

An octree cells occupancy geometric dimensionality descriptor for massive on-server point cloud visualisation and classification

Lidar datasets are becoming more and more common. They are appreciated f...

Please sign up or login with your details

Forgot password? Click here to reset