3D Point Cloud Registration with Multi-Scale Architecture and Self-supervised Fine-tuning

03/26/2021
by   Sofiane Horache, et al.
0

We present MS-SVConv, a fast multi-scale deep neural network that outputs features from point clouds for 3D registration between two scenes. We compute features using a 3D sparse voxel convolutional network on a point cloud at different scales and then fuse the features through fully-connected layers. With supervised learning, we show significant improvements compared to state-of-the-art methods on the competitive and well-known 3DMatch benchmark. We also achieve a better generalization through different source and target datasets, with very fast computation. Finally, we present a strategy to fine-tune MS-SVConv on unknown datasets in a self-supervised way, which leads to state-of-the-art results on ETH and TUM datasets.

READ FULL TEXT

page 5

page 12

page 18

page 19

research
04/12/2021

A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds

Deep neural networks have achieved promising performance in supervised p...
research
08/22/2022

PU-MFA : Point Cloud Up-sampling via Multi-scale Features Attention

Recently, research using point clouds has been increasing with the devel...
research
03/11/2020

Self-supervised Point Set Local Descriptors for Point Cloud Registration

In this work, we propose to learn local descriptors for point clouds in ...
research
01/28/2022

Neighborhood-aware Geometric Encoding Network for Point Cloud Registration

The distinguishing geometric features determine the success of point clo...
research
06/18/2019

Neural Multi-Scale Self-Supervised Registration for Echocardiogram Dense Tracking

Echocardiography has become routinely used in the diagnosis of cardiomyo...
research
03/06/2020

D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features

A successful point cloud registration often lies on robust establishment...
research
02/10/2023

Boosting 3D Point Cloud Registration by Transferring Multi-modality Knowledge

The recent multi-modality models have achieved great performance in many...

Please sign up or login with your details

Forgot password? Click here to reset