{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/3d-point-cloud-registration-with-multi-scale","title":"3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning","arxiv_id":"2103.14533","date":"2021-03-26","proceeding":null,"authors":["Sofiane Horache","Jean-Emmanuel Deschaud","François Goulette"],"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, 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 .","url_abs":"https://arxiv.org/abs/2103.14533v2","url_pdf":"https://arxiv.org/pdf/2103.14533v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"3d-point-cloud-registration-with-multi-scale","repo_url":"https://github.com/humanpose1/MS-SVConv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"point-cloud-registration","task_name":"Point Cloud Registration"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"tum","method_name":"TUM"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-cloud-registration-on-3dmatch-benchmark","task":"Point Cloud Registration","dataset":"3DMatch Benchmark","model":"MS-SVConv","rank_in_archive_order":2,"of":15,"metrics":{"Feature Matching Recall":"98.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}