DSAC - Differentiable RANSAC for Camera Localization
RANSAC is an important algorithm in robust optimization and a central building block for many computer vision applications. In recent years, traditionally hand-crafted pipelines have been replaced by deep learning pipelines, which can be trained in an end-to-end fashion. However, RANSAC has so far n...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
21.03.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | RANSAC is an important algorithm in robust optimization and a central building block for many computer vision applications. In recent years, traditionally hand-crafted pipelines have been replaced by deep learning pipelines, which can be trained in an end-to-end fashion. However, RANSAC has so far not been used as part of such deep learning pipelines, because its hypothesis selection procedure is non-differentiable. In this work, we present two different ways to overcome this limitation. The most promising approach is inspired by reinforcement learning, namely to replace the deterministic hypothesis selection by a probabilistic selection for which we can derive the expected loss w.r.t. to all learnable parameters. We call this approach DSAC, the differentiable counterpart of RANSAC. We apply DSAC to the problem of camera localization, where deep learning has so far failed to improve on traditional approaches. We demonstrate that by directly minimizing the expected loss of the output camera poses, robustly estimated by RANSAC, we achieve an increase in accuracy. In the future, any deep learning pipeline can use DSAC as a robust optimization component. |
---|---|
AbstractList | RANSAC is an important algorithm in robust optimization and a central building block for many computer vision applications. In recent years, traditionally hand-crafted pipelines have been replaced by deep learning pipelines, which can be trained in an end-to-end fashion. However, RANSAC has so far not been used as part of such deep learning pipelines, because its hypothesis selection procedure is non-differentiable. In this work, we present two different ways to overcome this limitation. The most promising approach is inspired by reinforcement learning, namely to replace the deterministic hypothesis selection by a probabilistic selection for which we can derive the expected loss w.r.t. to all learnable parameters. We call this approach DSAC, the differentiable counterpart of RANSAC. We apply DSAC to the problem of camera localization, where deep learning has so far failed to improve on traditional approaches. We demonstrate that by directly minimizing the expected loss of the output camera poses, robustly estimated by RANSAC, we achieve an increase in accuracy. In the future, any deep learning pipeline can use DSAC as a robust optimization component. |
Author | Brachmann, Eric Rother, Carsten Shotton, Jamie Krull, Alexander Nowozin, Sebastian Gumhold, Stefan Michel, Frank |
Author_xml | – sequence: 1 givenname: Eric surname: Brachmann fullname: Brachmann, Eric – sequence: 2 givenname: Alexander surname: Krull fullname: Krull, Alexander – sequence: 3 givenname: Sebastian surname: Nowozin fullname: Nowozin, Sebastian – sequence: 4 givenname: Jamie surname: Shotton fullname: Shotton, Jamie – sequence: 5 givenname: Frank surname: Michel fullname: Michel, Frank – sequence: 6 givenname: Stefan surname: Gumhold fullname: Gumhold, Stefan – sequence: 7 givenname: Carsten surname: Rother fullname: Rother, Carsten |
BookMark | eNrjYmDJy89LZWLgNDI2NtS1MDEy4mDgLS7OMjAwMDIzNzI1NeZkMHEJdnRW0FVwyUxLSy1KzSvJTEzKSVUIcvQDiaflFyk4J-amFiUq-OQnJ-ZkViWWZObn8TCwpiXmFKfyQmluBmU31xBnD92CovzC0tTikvis_NKiPKBUvJGBuaGFqaGRpZkxcaoAonY0lg |
ContentType | Paper |
Copyright | 2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Korea SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_20718512963 |
IEDL.DBID | 8FG |
IngestDate | Thu Oct 10 16:19:21 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_20718512963 |
OpenAccessLink | https://www.proquest.com/docview/2071851296?pq-origsite=%requestingapplication% |
PQID | 2071851296 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2071851296 |
PublicationCentury | 2000 |
PublicationDate | 20180321 |
PublicationDateYYYYMMDD | 2018-03-21 |
PublicationDate_xml | – month: 03 year: 2018 text: 20180321 day: 21 |
PublicationDecade | 2010 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2018 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.143017 |
SecondaryResourceType | preprint |
Snippet | RANSAC is an important algorithm in robust optimization and a central building block for many computer vision applications. In recent years, traditionally... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Algorithms Cameras Computer vision Hypotheses Localization Machine learning Optimization Pipelines |
Title | DSAC - Differentiable RANSAC for Camera Localization |
URI | https://www.proquest.com/docview/2071851296 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LSwMxEB60i-DNJz5qCeg1YDYx3T1J3e5axC6lKvRWskk8idZuvfrbnQmpHoRCLkkgCSGZb-ZLZgbgSuQ-VdY1XGqbcyWd5LnUhlOkGH3tDCIaOTiPaz16UQ-zm1kk3Nr4rXItE4Ogdh-WOHJiQhBaEJ307eKTU9Yoel2NKTS2IREUCY88xav7X44l1X3UmOU_MRuwo9qDZGIWfrkPW_79AHbCl0vbHoIaPg0KxtkwpijBq9a8eTYd1NSOuiQrDDFG7JHgJrpLHsFlVT4XI76eah4PQzv_W7o8hg5a9f4EmBFa465YrbCoVzQ8nMws6gNS-H5ms1PobhrpbHP3OewisgfnuVR0obNafvkLRM9V0wtb1IPkrqwnU6yNv8sf2ih2_A |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwED-0RfTNT_yYGtDXgG1i1j7J7DaqdmXMCXsraRKfhs51_v_elUwfhEGeEkjCkdzv7pe7HMBtlLpYGltzoUzKpbCCp0JpTj_FqDurEdEowXlUqvxNPs_uZ55wa3xY5VontorafhriyIkJQWhBdFIPiy9OVaPoddWX0NiGkL7cTAIIHwflePLLssSqizaz-KdoW_QY7kM41gu3PIAt93EIO23QpWmOQPZfexnjrO-LlOBlq-eOTXol9aM1yTJNnBErCHB8wuQx3AwH0yzn66Uqfxya6m_z4gQC9OvdKTAdKYVyMUpik-_oeliRGLQIROS6iUnOoLNppvPNw9ewm09HRVU8lS8XsIc436bSxVEHgtXy210ilq7qKy-wHxgZeIg |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=DSAC+-+Differentiable+RANSAC+for+Camera+Localization&rft.jtitle=arXiv.org&rft.au=Brachmann%2C+Eric&rft.au=Krull%2C+Alexander&rft.au=Nowozin%2C+Sebastian&rft.au=Shotton%2C+Jamie&rft.date=2018-03-21&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |