{"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/s2dnet-learning-accurate-correspondences-for","title":"S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching","arxiv_id":"2004.01673","date":"2020-04-03","proceeding":null,"authors":["Hugo Germain","Guillaume Bourmaud","Vincent Lepetit"],"abstract":"Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust correspondences under challenging conditions, they are often limited in terms of precision. In this paper, we introduce S2DNet, a novel feature matching pipeline, designed and trained to efficiently establish both robust and accurate correspondences. By leveraging a sparse-to-dense matching paradigm, we cast the correspondence learning problem as a supervised classification task to learn to output highly peaked correspondence maps. We show that S2DNet achieves state-of-the-art results on the HPatches benchmark, as well as on several long-term visual localization datasets.","url_abs":"https://arxiv.org/abs/2004.01673v1","url_pdf":"https://arxiv.org/pdf/2004.01673v1.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":"s2dnet-learning-accurate-correspondences-for","repo_url":"https://github.com/germain-hug/S2DNet-Minimal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"s2dnet-learning-accurate-correspondences-for","repo_url":"https://github.com/MindSpore-scientific/code-14/tree/main/S2DNet-Minimal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"s2dnet-learning-accurate-correspondences-for","repo_url":"https://github.com/MindSpore-scientific/code-5/tree/main/S2DNet-Minimal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"s2dnet-learning-accurate-correspondences-for","repo_url":"https://github.com/zhuyuhua1/contrib/tree/s2dnet/application/S2DNet-Minimal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"visual-localization","task_name":"Visual Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.01673","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}