Neural-Guided RANSAC: learning where to sample model hypotheses
We present Neural-Guided RANSAC (NG-RANSAC), an extension to the classic RANSAC algorithm from robust optimization. NG-RANSAC uses prior information to improve model hypothesis search, increasing the chance of finding outlier-free minimal sets. Previous works use heuristic side-information like hand...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Dokumenttyp: | Article (Journal) Kapitel/Artikel |
| Sprache: | Englisch |
| Veröffentlicht: |
31 Jul 2019
|
| In: |
Arxiv
|
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/1905.04132
|
| Verfasserangaben: | Eric Brachmann and Carsten Rother |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1731809948 | ||
| 003 | DE-627 | ||
| 005 | 20220818195528.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 200914s2019 xx |||||o 00| ||eng c | ||
| 035 | |a (DE-627)1731809948 | ||
| 035 | |a (DE-599)KXP1731809948 | ||
| 035 | |a (OCoLC)1341359537 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 28 |2 sdnb | ||
| 100 | 1 | |a Brachmann, Eric |d 1987- |e VerfasserIn |0 (DE-588)1179206088 |0 (DE-627)1066600457 |0 (DE-576)518117634 |4 aut | |
| 245 | 1 | 0 | |a Neural-Guided RANSAC |b learning where to sample model hypotheses |c Eric Brachmann and Carsten Rother |
| 264 | 1 | |c 31 Jul 2019 | |
| 300 | |a 17 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 14.09.2020 | ||
| 520 | |a We present Neural-Guided RANSAC (NG-RANSAC), an extension to the classic RANSAC algorithm from robust optimization. NG-RANSAC uses prior information to improve model hypothesis search, increasing the chance of finding outlier-free minimal sets. Previous works use heuristic side-information like hand-crafted descriptor distance to guide hypothesis search. In contrast, we learn hypothesis search in a principled fashion that lets us optimize an arbitrary task loss during training, leading to large improvements on classic computer vision tasks. We present two further extensions to NG-RANSAC. Firstly, using the inlier count itself as training signal allows us to train neural guidance in a self-supervised fashion. Secondly, we combine neural guidance with differentiable RANSAC to build neural networks which focus on certain parts of the input data and make the output predictions as good as possible. We evaluate NG-RANSAC on a wide array of computer vision tasks, namely estimation of epipolar geometry, horizon line estimation and camera re-localization. We achieve superior or competitive results compared to state-of-the-art robust estimators, including very recent, learned ones. | ||
| 650 | 4 | |a Computer Science - Computer Vision and Pattern Recognition | |
| 700 | 1 | |a Rother, Carsten |e VerfasserIn |0 (DE-588)1181464692 |0 (DE-627)1662676883 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Arxiv |d Ithaca, NY : Cornell University, 1991 |g (2019) Artikel-Nummer 1905-04132, 17 Seiten |h Online-Ressource |w (DE-627)509006531 |w (DE-600)2225896-6 |w (DE-576)28130436X |7 nnas |a Neural-Guided RANSAC learning where to sample model hypotheses |
| 773 | 1 | 8 | |g year:2019 |g extent:17 |a Neural-Guided RANSAC learning where to sample model hypotheses |
| 787 | 0 | 8 | |i Forschungsdaten |a Brachmann, Eric, 1987 - |t Neural-Guided RANSAC for estimating epipolar geometry [data] |d Heidelberg : Universität, 2020 |h 1 Online-Ressource (1 File) |w (DE-627)1731809190 |
| 856 | 4 | 0 | |u http://arxiv.org/abs/1905.04132 |x Verlag |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20200914 | ||
| 993 | |a Article | ||
| 994 | |a 2020 | ||
| 998 | |g 1181464692 |a Rother, Carsten |m 1181464692:Rother, Carsten |d 700000 |d 708070 |d 700000 |d 728500 |e 700000PR1181464692 |e 708070PR1181464692 |e 700000PR1181464692 |e 728500PR1181464692 |k 0/700000/ |k 1/700000/708070/ |k 0/700000/ |k 1/700000/728500/ |p 2 |y j | ||
| 998 | |g 1179206088 |a Brachmann, Eric |m 1179206088:Brachmann, Eric |d 700000 |d 708070 |e 700000PB1179206088 |e 708070PB1179206088 |k 0/700000/ |k 1/700000/708070/ |p 1 |x j | ||
| 999 | |a KXP-PPN1731809948 |e 375294918X | ||
| BIB | |a Y | ||
| JSO | |a {"relHost":[{"origin":[{"dateIssuedDisp":"1991-","publisher":"Cornell University ; Arxiv.org","dateIssuedKey":"1991","publisherPlace":"Ithaca, NY ; [Erscheinungsort nicht ermittelbar]"}],"id":{"eki":["509006531"],"zdb":["2225896-6"]},"physDesc":[{"extent":"Online-Ressource"}],"title":[{"title_sort":"Arxiv","title":"Arxiv"}],"disp":"Neural-Guided RANSAC learning where to sample model hypothesesArxiv","note":["Gesehen am 28.05.2024"],"type":{"bibl":"edited-book","media":"Online-Ressource"},"recId":"509006531","language":["eng"],"pubHistory":["1991 -"],"part":{"text":"(2019) Artikel-Nummer 1905-04132, 17 Seiten","extent":"17","year":"2019"},"titleAlt":[{"title":"Arxiv.org"},{"title":"Arxiv.org e-print archive"},{"title":"Arxiv e-print archive"},{"title":"De.arxiv.org"}]}],"physDesc":[{"extent":"17 S."}],"name":{"displayForm":["Eric Brachmann and Carsten Rother"]},"id":{"eki":["1731809948"]},"origin":[{"dateIssuedKey":"2019","dateIssuedDisp":"31 Jul 2019"}],"recId":"1731809948","language":["eng"],"type":{"bibl":"chapter","media":"Online-Ressource"},"note":["Gesehen am 14.09.2020"],"person":[{"family":"Brachmann","given":"Eric","roleDisplay":"VerfasserIn","display":"Brachmann, Eric","role":"aut"},{"display":"Rother, Carsten","roleDisplay":"VerfasserIn","role":"aut","family":"Rother","given":"Carsten"}],"title":[{"title_sort":"Neural-Guided RANSAC","subtitle":"learning where to sample model hypotheses","title":"Neural-Guided RANSAC"}]} | ||
| SRT | |a BRACHMANNENEURALGUID3120 | ||