S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching

S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching. Germain, H., Bourmaud, G., & Lepetit, V. 2020.

Website abstract bibtex

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.

@article{
 title = {S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching},
 type = {article},
 year = {2020},
 keywords = {classification,feature matching,visual localization},
 pages = {11-13},
 websites = {http://arxiv.org/abs/2004.01673},
 id = {c18e7e69-95fb-3cfe-a6bf-5b6261bf2947},
 created = {2022-09-19T09:01:25.013Z},
 file_attached = {true},
 profile_id = {276016a7-2c9d-3507-8888-093db7c54774},
 group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
 last_modified = {2022-09-22T17:08:08.907Z},
 read = {true},
 starred = {true},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100,1608176d-7332-416b-a03b-89c3f2ae3ab6},
 private_publication = {false},
 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.},
 bibtype = {article},
 author = {Germain, Hugo and Bourmaud, Guillaume and Lepetit, Vincent}
}

Downloads: 0

{"_id":"Qo7xjC8NnpCMvwekC","bibbaseid":"germain-bourmaud-lepetit-s2dnetlearningaccuratecorrespondencesforsparsetodensefeaturematching-2020","authorIDs":[],"author_short":["Germain, H.","Bourmaud, G.","Lepetit, V."],"bibdata":{"title":"S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching","type":"article","year":"2020","keywords":"classification,feature matching,visual localization","pages":"11-13","websites":"http://arxiv.org/abs/2004.01673","id":"c18e7e69-95fb-3cfe-a6bf-5b6261bf2947","created":"2022-09-19T09:01:25.013Z","file_attached":"true","profile_id":"276016a7-2c9d-3507-8888-093db7c54774","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2022-09-22T17:08:08.907Z","read":"true","starred":"true","authored":false,"confirmed":"true","hidden":false,"folder_uuids":"02fb5526-03ff-44ad-8d5c-42bd496c3100,1608176d-7332-416b-a03b-89c3f2ae3ab6","private_publication":false,"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.","bibtype":"article","author":"Germain, Hugo and Bourmaud, Guillaume and Lepetit, Vincent","bibtex":"@article{\n title = {S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching},\n type = {article},\n year = {2020},\n keywords = {classification,feature matching,visual localization},\n pages = {11-13},\n websites = {http://arxiv.org/abs/2004.01673},\n id = {c18e7e69-95fb-3cfe-a6bf-5b6261bf2947},\n created = {2022-09-19T09:01:25.013Z},\n file_attached = {true},\n profile_id = {276016a7-2c9d-3507-8888-093db7c54774},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2022-09-22T17:08:08.907Z},\n read = {true},\n starred = {true},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100,1608176d-7332-416b-a03b-89c3f2ae3ab6},\n private_publication = {false},\n 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.},\n bibtype = {article},\n author = {Germain, Hugo and Bourmaud, Guillaume and Lepetit, Vincent}\n}","author_short":["Germain, H.","Bourmaud, G.","Lepetit, V."],"urls":{"Website":"http://arxiv.org/abs/2004.01673"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"germain-bourmaud-lepetit-s2dnetlearningaccuratecorrespondencesforsparsetodensefeaturematching-2020","role":"author","keyword":["classification","feature matching","visual localization"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","creationDate":"2020-04-06T16:04:12.904Z","downloads":0,"keywords":["classification","feature matching","visual localization"],"search_terms":["s2dnet","learning","accurate","correspondences","sparse","dense","feature","matching","germain","bourmaud","lepetit"],"title":"S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching","year":2020,"dataSources":["FbFoGuouoJnLoBjsv","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"]}