Visual camera re-localization from RGB and RGB-D images using DSAC
We describe a learning-based system that estimates the camera position and orientation from a single input image relative to a known environment. The system is flexible w.r.t. the amount of information available at test and at training time, catering to different applications. Input images can be RG...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
01 September 2022
|
| In: |
IEEE transactions on pattern analysis and machine intelligence
Year: 2022, Jahrgang: 44, Heft: 9, Pages: 5847-5865 |
| ISSN: | 1939-3539 |
| DOI: | 10.1109/TPAMI.2021.3070754 |
| Online-Zugang: | Resolving-System, kostenfrei, Volltext: https://doi.org/10.1109/TPAMI.2021.3070754 Verlag, kostenfrei, Volltext: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9394752 
|
| Verfasserangaben: | Eric Brachmann and Carsten Rother |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1819043193 | ||
| 003 | DE-627 | ||
| 005 | 20230118141915.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 221017s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TPAMI.2021.3070754 |2 doi | |
| 035 | |a (DE-627)1819043193 | ||
| 035 | |a (DE-599)KXP1819043193 | ||
| 035 | |a (OCoLC)1361695615 | ||
| 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 Visual camera re-localization from RGB and RGB-D images using DSAC |c Eric Brachmann and Carsten Rother |
| 264 | 1 | |c 01 September 2022 | |
| 300 | |a 19 | ||
| 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 17.10.2022 | ||
| 520 | |a We describe a learning-based system that estimates the camera position and orientation from a single input image relative to a known environment. The system is flexible w.r.t. the amount of information available at test and at training time, catering to different applications. Input images can be RGB-D or RGB, and a 3D model of the environment can be utilized for training but is not necessary. In the minimal case, our system requires only RGB images and ground truth poses at training time, and it requires only a single RGB image at test time. The framework consists of a deep neural network and fully differentiable pose optimization. The neural network predicts so called scene coordinates, i.e., dense correspondences between the input image and 3D scene space of the environment. The pose optimization implements robust fitting of pose parameters using differentiable RANSAC (DSAC) to facilitate end-to-end training. The system, an extension of DSAC and referred to as DSAC*, achieves state-of-the-art accuracy on various public datasets for RGB-based re-localization, and competitive accuracy for RGB-D based re-localization. | ||
| 700 | 1 | |a Rother, Carsten |e VerfasserIn |0 (DE-588)1181464692 |0 (DE-627)1662676883 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |a Institute of Electrical and Electronics Engineers |t IEEE transactions on pattern analysis and machine intelligence |d New York, NY : IEEE, 1979 |g 44(2022), 9, Seite 5847-5865 |h Online-Ressource |w (DE-627)324486421 |w (DE-600)2027336-8 |w (DE-576)094110980 |x 1939-3539 |7 nnas |
| 773 | 1 | 8 | |g volume:44 |g year:2022 |g number:9 |g pages:5847-5865 |g extent:19 |a Visual camera re-localization from RGB and RGB-D images using DSAC |
| 856 | 4 | 0 | |u https://doi.org/10.1109/TPAMI.2021.3070754 |x Resolving-System |x Verlag |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9394752 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20221017 | ||
| 993 | |a Article | ||
| 994 | |a 2022 | ||
| 998 | |g 1181464692 |a Rother, Carsten |m 1181464692:Rother, Carsten |d 700000 |d 708070 |e 700000PR1181464692 |e 708070PR1181464692 |k 0/700000/ |k 1/700000/708070/ |p 2 |y j | ||
| 998 | |g 1179206088 |a Brachmann, Eric |m 1179206088:Brachmann, Eric |p 1 |x j | ||
| 999 | |a KXP-PPN1819043193 |e 4198073015 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"title":[{"title_sort":"Visual camera re-localization from RGB and RGB-D images using DSAC","title":"Visual camera re-localization from RGB and RGB-D images using DSAC"}],"person":[{"roleDisplay":"VerfasserIn","display":"Brachmann, Eric","role":"aut","family":"Brachmann","given":"Eric"},{"role":"aut","display":"Rother, Carsten","roleDisplay":"VerfasserIn","given":"Carsten","family":"Rother"}],"note":["Gesehen am 17.10.2022"],"type":{"media":"Online-Ressource","bibl":"article-journal"},"recId":"1819043193","language":["eng"],"origin":[{"dateIssuedDisp":"01 September 2022","dateIssuedKey":"2022"}],"id":{"eki":["1819043193"],"doi":["10.1109/TPAMI.2021.3070754"]},"name":{"displayForm":["Eric Brachmann and Carsten Rother"]},"physDesc":[{"extent":"19 S."}],"relHost":[{"physDesc":[{"extent":"Online-Ressource"}],"name":{"displayForm":["Institute of Electrical and Electronics Engineers"]},"id":{"issn":["1939-3539"],"zdb":["2027336-8"],"eki":["324486421"]},"origin":[{"publisherPlace":"New York, NY","dateIssuedDisp":"1979-","publisher":"IEEE","dateIssuedKey":"1979"}],"language":["eng"],"corporate":[{"role":"aut","display":"Institute of Electrical and Electronics Engineers","roleDisplay":"VerfasserIn"}],"recId":"324486421","disp":"Institute of Electrical and Electronics EngineersIEEE transactions on pattern analysis and machine intelligence","type":{"media":"Online-Ressource","bibl":"periodical"},"note":["Gesehen am 07. März 2019"],"titleAlt":[{"title":"Transactions on pattern analysis and machine intelligence"},{"title":"TPAMI"}],"part":{"pages":"5847-5865","issue":"9","year":"2022","extent":"19","text":"44(2022), 9, Seite 5847-5865","volume":"44"},"pubHistory":["1.1979 -"],"title":[{"title":"IEEE transactions on pattern analysis and machine intelligence","subtitle":"TPAMI","title_sort":"IEEE transactions on pattern analysis and machine intelligence"}]}]} | ||
| SRT | |a BRACHMANNEVISUALCAME0120 | ||