SuperPoint: Self-supervised interest point detection and description. Detone, D., Malisiewicz, T., & Rabinovich, A. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2018-June:337-349, 2018.
![SuperPoint: Self-supervised interest point detection and description [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper doi abstract bibtex
Paper doi abstract bibtex This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision. As opposed to patch-based neural networks, our fully-convolutional model operates on full-sized images and jointly computes pixel-level interest point locations and associated descriptors in one forward pass. We introduce Homographic Adaptation, a multi-scale, multi-homography approach for boosting interest point detection repeatability and performing cross-domain adaptation (e.g., synthetic-to-real). Our model, when trained on the MS-COCO generic image dataset using Homographic Adaptation, is able to repeatedly detect a much richer set of interest points than the initial pre-adapted deep model and any other traditional corner detector. The final system gives rise to state-of-the-art homography estimation results on HPatches when compared to LIFT, SIFT and ORB.
@article{
title = {SuperPoint: Self-supervised interest point detection and description},
type = {article},
year = {2018},
pages = {337-349},
volume = {2018-June},
id = {bc0e0485-218f-331b-a9fa-db8a193b6669},
created = {2022-09-19T09:01:25.220Z},
file_attached = {true},
profile_id = {276016a7-2c9d-3507-8888-093db7c54774},
group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
last_modified = {2022-10-07T07:18:24.263Z},
read = {true},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100,1608176d-7332-416b-a03b-89c3f2ae3ab6},
private_publication = {false},
abstract = {This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision. As opposed to patch-based neural networks, our fully-convolutional model operates on full-sized images and jointly computes pixel-level interest point locations and associated descriptors in one forward pass. We introduce Homographic Adaptation, a multi-scale, multi-homography approach for boosting interest point detection repeatability and performing cross-domain adaptation (e.g., synthetic-to-real). Our model, when trained on the MS-COCO generic image dataset using Homographic Adaptation, is able to repeatedly detect a much richer set of interest points than the initial pre-adapted deep model and any other traditional corner detector. The final system gives rise to state-of-the-art homography estimation results on HPatches when compared to LIFT, SIFT and ORB.},
bibtype = {article},
author = {Detone, Daniel and Malisiewicz, Tomasz and Rabinovich, Andrew},
doi = {10.1109/CVPRW.2018.00060},
journal = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops}
}Downloads: 0
{"_id":"Z6NvXnEAHTa8CeS4Z","bibbaseid":"detone-malisiewicz-rabinovich-superpointselfsupervisedinterestpointdetectionanddescription-2018","author_short":["Detone, D.","Malisiewicz, T.","Rabinovich, A."],"bibdata":{"title":"SuperPoint: Self-supervised interest point detection and description","type":"article","year":"2018","pages":"337-349","volume":"2018-June","id":"bc0e0485-218f-331b-a9fa-db8a193b6669","created":"2022-09-19T09:01:25.220Z","file_attached":"true","profile_id":"276016a7-2c9d-3507-8888-093db7c54774","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2022-10-07T07:18:24.263Z","read":"true","starred":false,"authored":false,"confirmed":"true","hidden":false,"folder_uuids":"02fb5526-03ff-44ad-8d5c-42bd496c3100,1608176d-7332-416b-a03b-89c3f2ae3ab6","private_publication":false,"abstract":"This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision. As opposed to patch-based neural networks, our fully-convolutional model operates on full-sized images and jointly computes pixel-level interest point locations and associated descriptors in one forward pass. We introduce Homographic Adaptation, a multi-scale, multi-homography approach for boosting interest point detection repeatability and performing cross-domain adaptation (e.g., synthetic-to-real). Our model, when trained on the MS-COCO generic image dataset using Homographic Adaptation, is able to repeatedly detect a much richer set of interest points than the initial pre-adapted deep model and any other traditional corner detector. The final system gives rise to state-of-the-art homography estimation results on HPatches when compared to LIFT, SIFT and ORB.","bibtype":"article","author":"Detone, Daniel and Malisiewicz, Tomasz and Rabinovich, Andrew","doi":"10.1109/CVPRW.2018.00060","journal":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","bibtex":"@article{\n title = {SuperPoint: Self-supervised interest point detection and description},\n type = {article},\n year = {2018},\n pages = {337-349},\n volume = {2018-June},\n id = {bc0e0485-218f-331b-a9fa-db8a193b6669},\n created = {2022-09-19T09:01:25.220Z},\n file_attached = {true},\n profile_id = {276016a7-2c9d-3507-8888-093db7c54774},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2022-10-07T07:18:24.263Z},\n read = {true},\n starred = {false},\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 = {This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision. As opposed to patch-based neural networks, our fully-convolutional model operates on full-sized images and jointly computes pixel-level interest point locations and associated descriptors in one forward pass. We introduce Homographic Adaptation, a multi-scale, multi-homography approach for boosting interest point detection repeatability and performing cross-domain adaptation (e.g., synthetic-to-real). Our model, when trained on the MS-COCO generic image dataset using Homographic Adaptation, is able to repeatedly detect a much richer set of interest points than the initial pre-adapted deep model and any other traditional corner detector. The final system gives rise to state-of-the-art homography estimation results on HPatches when compared to LIFT, SIFT and ORB.},\n bibtype = {article},\n author = {Detone, Daniel and Malisiewicz, Tomasz and Rabinovich, Andrew},\n doi = {10.1109/CVPRW.2018.00060},\n journal = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops}\n}","author_short":["Detone, D.","Malisiewicz, T.","Rabinovich, A."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/321f63da-6739-79db-583a-0523ab386b12/DeTone_SuperPoint_Self_Supervised_Interest_CVPR_2018_paper.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"detone-malisiewicz-rabinovich-superpointselfsupervisedinterestpointdetectionanddescription-2018","role":"author","metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["superpoint","self","supervised","interest","point","detection","description","detone","malisiewicz","rabinovich"],"title":"SuperPoint: Self-supervised interest point detection and description","year":2018}