Skip to Main content Skip to Navigation
Journal articles

3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised transfer learning

Abstract : 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.
Document type :
Journal articles
Complete list of metadata

https://hal-mines-paristech.archives-ouvertes.fr/hal-03203390
Contributor : François Goulette Connect in order to contact the contributor
Submitted on : Tuesday, April 20, 2021 - 6:00:26 PM
Last modification on : Friday, January 14, 2022 - 11:38:16 AM

Links full text

Identifiers

Citation

Sofiane Horache, Jean-Emmanuel Deschaud, Francois Goulette. 3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised transfer learning. 2021 International Conference on 3D Vision (3DV), 2021, ⟨10.1109/3DV53792.2021.00142⟩. ⟨hal-03203390⟩

Share

Metrics

Record views

105