3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We propose a method for generalizing deep learning for 3D point cloud registration on new,totally different datasets. It is based on two components,MS-SVConv and UDGE. Using Multi-Scale Sparse Voxel Convolution,MSSVConv is a fast deep neural network that outputs the descriptors from point clouds for 3D registration between two scenes. UDGE is an algorithm for transferring deep networks on unknown datasets in a unsupervised way. The interest of the proposed method appears while using the two components,MS-SVConv and UDGE,together as a whole,which leads to state-of-the-art results on real world registration datasets such as 3DMatch,ETH and TUM. The code is publicly available at https://github.com/humanpose1/MS-SVConv.

Original languageEnglish
Title of host publicationProceedings - 2021 International Conference on 3D Vision, 3DV 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1351-1361
Number of pages11
ISBN (Electronic)9781665426886
DOIs
Publication statusPublished - 1 Jan 2021
Externally publishedYes
Event9th International Conference on 3D Vision, 3DV 2021 - Virtual, Online, United Kingdom
Duration: 1 Dec 20213 Dec 2021

Publication series

NameProceedings - 2021 International Conference on 3D Vision, 3DV 2021

Conference

Conference9th International Conference on 3D Vision, 3DV 2021
Country/TerritoryUnited Kingdom
CityVirtual, Online
Period1/12/213/12/21

Keywords

  • 3D Point Cloud
  • Deep Learning
  • Registration

Fingerprint

Dive into the research topics of '3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning'. Together they form a unique fingerprint.

Cite this