{"url":"/method/rpm-net","slug":"rpm-net","name":"RPM-Net","full_name":"RPM-Net","full_name_withheld":false,"description_markdown":"**RPM-Net** is an end-to-end differentiable deep network for robust point matching uses learned features. It preserves robustness of RPM against noisy/outlier points while desensitizing initialization with point correspondences from learned feature distances instead of spatial distances. The network uses the differentiable Sinkhorn layer and annealing to get soft assignments of point correspondences from hybrid features learned from both spatial coordinates and local geometry. To further improve registration performance, the authors introduce a secondary network to predict optimal annealing parameters.","description_state":"present","introduced_year":null,"introduced_by":{"title":"RPM-Net: Robust Point Matching using Learned Features","paper":"/paper/2003-13479","first_author":"Zi Jian Yew","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/2003-13479"},"source":{"url":"https://arxiv.org/abs/2003.13479v1","title":"RPM-Net: Robust Point Matching using Learned Features","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Point Cloud Models","url":"/methods/category/point-cloud-models","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":null,"title":"Deep Weighted Consensus: Dense correspondence confidence maps for 3D shape registration","date":"2021-05-06","arxiv_id":"2105.02714","n_code_links":0,"syntology":null},{"paper":"/paper/2003-13479","title":"RPM-Net: Robust Point Matching using Learned Features","date":"2020-03-30","arxiv_id":"2003.13479","n_code_links":5,"syntology":{"ran":6,"of":31,"unverified":25,"pointer_only":14}}],"papers_shown":2,"tasks":[{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/point-cloud-registration","name":"Point Cloud Registration","papers":1}],"tasks_shown":2,"n_tasks":2,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/rpm-net"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}