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


Sofiane Horache, Jean-Emmanuel Deschaud and Fran├žois Goulette


We present Multi-Scale Sparse Voxel Convolution (MS-SVConv), a fast multi-scale deep neural network that outputs the descriptors from point clouds for 3D registration between two scenes. We compute descriptors using a 3D sparse voxel convolutional network on a point cloud at different scales and then fuse the descriptors 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 better generalization through different source and target datasets, with very fast computation. Finally, we present a strategy for transferring MS-SVConv on unknown datasets in a unsupervised way called UDGE, which leads to state-of-the-art results on the ETH and TUM datasets. [The code will be publicly available before publication].

PDF (protected)

  Important Dates

All deadlines are 23:59 Pacific Time (PT). No extensions will be granted.

Paper registration July 23 30, 2021
Paper submission July 30, 2021
Supplementary August 8, 2021
Tutorial submission August 15, 2021
Tutorial notification August 31, 2021
Rebuttal period September 16-22, 2021
Paper notification October 1, 2021
Camera ready October 15, 2021
Demo submission July 30 Nov 15, 2021
Demo notification Oct 1 Nov 19, 2021
Tutorial November 30, 2021
Main conference December 1-3, 2021