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. arXiv:2004.01673 [cs], 4, 2020.

Paper

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

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 = {Computer Science - Computer Vision and Pattern Rec},
 websites = {http://arxiv.org/abs/2004.01673},
 month = {4},
 id = {e63e32c1-63e6-3668-9d6a-f1745573af59},
 created = {2022-03-28T09:45:06.461Z},
 accessed = {2022-01-03},
 file_attached = {true},
 profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},
 group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
 last_modified = {2022-03-29T07:59:36.087Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {germainS2DNetLearningAccurate2020},
 source_type = {article},
 short_title = {S2DNet},
 notes = {arXiv: 2004.01673},
 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},
 journal = {arXiv:2004.01673 [cs]}
}

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":"Computer Science - Computer Vision and Pattern Rec","websites":"http://arxiv.org/abs/2004.01673","month":"4","id":"e63e32c1-63e6-3668-9d6a-f1745573af59","created":"2022-03-28T09:45:06.461Z","accessed":"2022-01-03","file_attached":"true","profile_id":"235249c2-3ed4-314a-b309-b1ea0330f5d9","group_id":"1ff583c0-be37-34fa-9c04-73c69437d354","last_modified":"2022-03-29T07:59:36.087Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"germainS2DNetLearningAccurate2020","source_type":"article","short_title":"S2DNet","notes":"arXiv: 2004.01673","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","journal":"arXiv:2004.01673 [cs]","bibtex":"@article{\n title = {S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching},\n type = {article},\n year = {2020},\n keywords = {Computer Science - Computer Vision and Pattern Rec},\n websites = {http://arxiv.org/abs/2004.01673},\n month = {4},\n id = {e63e32c1-63e6-3668-9d6a-f1745573af59},\n created = {2022-03-28T09:45:06.461Z},\n accessed = {2022-01-03},\n file_attached = {true},\n profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},\n group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},\n last_modified = {2022-03-29T07:59:36.087Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {germainS2DNetLearningAccurate2020},\n source_type = {article},\n short_title = {S2DNet},\n notes = {arXiv: 2004.01673},\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 journal = {arXiv:2004.01673 [cs]}\n}","author_short":["Germain, H.","Bourmaud, G.","Lepetit, V."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/5267e9ab-07aa-2517-0192-2e8a253a8a1e/Germain_et_al___2020___S2DNet_Learning_Accurate_Correspondences_for_Spar.pdf.pdf","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":["Computer Science - Computer Vision and Pattern Rec"],"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":["computer science - computer vision and pattern rec"],"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"]}