TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Point Cloud Registration	3DMatch Benchmark	MS-SVConv	Feature Matching Recall	98.4	# 2

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/3d-point-cloud-registration-with-multi-scale/point-cloud-registration-on-3dmatch-benchmark)](https://paperswithcode.com/sota/point-cloud-registration-on-3dmatch-benchmark?p=3d-point-cloud-registration-with-multi-scale)`

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

26 Mar 2021 · Sofiane Horache, Jean-Emmanuel Deschaud, François Goulette ·

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, MS-SVConv 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 .

PDF Abstract