Expert Sample Consensus applied to camera re-localization

Fitting model parameters to a set of noisy data points is a common problem in computer vision. In this work, we fit the 6D camera pose to a set of noisy correspondences between the 2D input image and a known 3D environment. We estimate these correspondences from the image using a neural network. Sin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Brachmann, Eric (VerfasserIn) , Rother, Carsten (VerfasserIn)
Dokumenttyp: Article (Journal) Kapitel/Artikel
Sprache:Englisch
Veröffentlicht: 2019
In: Arxiv

Online-Zugang:Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/1908.02484
Volltext
Verfasserangaben:Eric Brachmann and Carsten Rother

MARC

LEADER 00000caa a2200000 c 4500
001 1731813082
003 DE-627
005 20220818195535.0
007 cr uuu---uuuuu
008 200914s2019 xx |||||o 00| ||eng c
035 |a (DE-627)1731813082 
035 |a (DE-599)KXP1731813082 
035 |a (OCoLC)1341359538 
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 Expert Sample Consensus applied to camera re-localization  |c Eric Brachmann and Carsten Rother 
264 1 |c 2019 
300 |a 13 
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 Fitting model parameters to a set of noisy data points is a common problem in computer vision. In this work, we fit the 6D camera pose to a set of noisy correspondences between the 2D input image and a known 3D environment. We estimate these correspondences from the image using a neural network. Since the correspondences often contain outliers, we utilize a robust estimator such as Random Sample Consensus (RANSAC) or Differentiable RANSAC (DSAC) to fit the pose parameters. When the problem domain, e.g. the space of all 2D-3D correspondences, is large or ambiguous, a single network does not cover the domain well. Mixture of Experts (MoE) is a popular strategy to divide a problem domain among an ensemble of specialized networks, so called experts, where a gating network decides which expert is responsible for a given input. In this work, we introduce Expert Sample Consensus (ESAC), which integrates DSAC in a MoE. Our main technical contribution is an efficient method to train ESAC jointly and end-to-end. We demonstrate experimentally that ESAC handles two real-world problems better than competing methods, i.e. scalability and ambiguity. We apply ESAC to fitting simple geometric models to synthetic images, and to camera re-localization for difficult, real datasets. 
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 1908.02484, 13 Seiten  |h Online-Ressource  |w (DE-627)509006531  |w (DE-600)2225896-6  |w (DE-576)28130436X  |7 nnas  |a Expert Sample Consensus applied to camera re-localization 
773 1 8 |g year:2019  |g extent:13  |a Expert Sample Consensus applied to camera re-localization 
787 0 8 |i Forschungsdaten  |a Brachmann, Eric, 1987 -   |t Expert Sample Consensus (ESAC) for visual re-localization [data]  |d Heidelberg : Universität, 2020  |h 1 Online-Ressource (7 Files)  |w (DE-627)1731811950 
856 4 0 |u http://arxiv.org/abs/1908.02484  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20200914 
993 |a Article 
994 |a 2019 
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-PPN1731813082  |e 375295776X 
BIB |a Y 
JSO |a {"title":[{"title_sort":"Expert Sample Consensus applied to camera re-localization","title":"Expert Sample Consensus applied to camera re-localization"}],"person":[{"family":"Brachmann","given":"Eric","display":"Brachmann, Eric","roleDisplay":"VerfasserIn","role":"aut"},{"given":"Carsten","family":"Rother","role":"aut","display":"Rother, Carsten","roleDisplay":"VerfasserIn"}],"language":["eng"],"recId":"1731813082","type":{"media":"Online-Ressource","bibl":"chapter"},"note":["Gesehen am 14.09.2020"],"id":{"eki":["1731813082"]},"origin":[{"dateIssuedDisp":"2019","dateIssuedKey":"2019"}],"name":{"displayForm":["Eric Brachmann and Carsten Rother"]},"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":"Arxiv","title_sort":"Arxiv"}],"pubHistory":["1991 -"],"titleAlt":[{"title":"Arxiv.org"},{"title":"Arxiv.org e-print archive"},{"title":"Arxiv e-print archive"},{"title":"De.arxiv.org"}],"part":{"year":"2019","text":"(2019) Artikel-Nummer 1908.02484, 13 Seiten","extent":"13"},"disp":"Expert Sample Consensus applied to camera re-localizationArxiv","type":{"bibl":"edited-book","media":"Online-Ressource"},"note":["Gesehen am 28.05.2024"],"language":["eng"],"recId":"509006531"}],"physDesc":[{"extent":"13 S."}]} 
SRT |a BRACHMANNEEXPERTSAMP2019