Zur Kurzanzeige

dc.contributor.author
Sakaridis, Christos
dc.contributor.author
Dai, Dengxin
dc.contributor.author
Hecker, Simon
dc.contributor.author
Van Gool, Luc
dc.contributor.editor
Ferrari, Vittorio
dc.contributor.editor
Hebert, Martial
dc.contributor.editor
Sminchisescu, Cristian
dc.contributor.editor
Weiss, Yair
dc.date.accessioned
2018-11-23T07:38:36Z
dc.date.available
2018-11-22T18:06:44Z
dc.date.available
2018-11-23T07:38:36Z
dc.date.issued
2018
dc.identifier.isbn
978-3-030-01260-1
en_US
dc.identifier.isbn
978-3-030-01261-8
en_US
dc.identifier.issn
0302-9743
dc.identifier.issn
1611-3349
dc.identifier.other
10.1007/978-3-030-01261-8_42
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/305722
dc.identifier.doi
10.3929/ethz-b-000305722
dc.description.abstract
This work addresses the problem of semantic scene understanding under dense fog. Although considerable progress has been made in semantic scene understanding, it is mainly related to clear-weather scenes. Extending recognition methods to adverse weather conditions such as fog is crucial for outdoor applications. In this paper, we propose a novel method, named Curriculum Model Adaptation (CMAda), which gradually adapts a semantic segmentation model from light synthetic fog to dense real fog in multiple steps, using both synthetic and real foggy data. In addition, we present three other main stand-alone contributions: 1) a novel method to add synthetic fog to real, clear-weather scenes using semantic input; 2) a new fog density estimator; 3) the Foggy Zurich dataset comprising 3808 real foggy images, with pixel-level semantic annotations for 16 images with dense fog. Our experiments show that 1) our fog simulation slightly outperforms a state-of-the-art competing simulation with respect to the task of semantic foggy scene understanding (SFSU); 2) CMAda improves the performance of state-of-the-art models for SFSU significantly by leveraging unlabeled real foggy data. The datasets and code will be made publicly available.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
Springer
en_US
dc.subject
Semantic foggy scene understanding
en_US
dc.subject
Fog simulation
en_US
dc.subject
Synthetic data
en_US
dc.subject
Curriculum model adaptation
en_US
dc.subject
Curriculum learning
en_US
dc.title
Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding
en_US
dc.type
Conference Paper
dc.date.published
2018-10-06
ethz.book.title
Computer Vision – ECCV 2018 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIII
en_US
ethz.journal.title
Lecture Notes in Computer Science
ethz.journal.volume
11217
en_US
ethz.journal.abbreviated
LNCS
ethz.pages.start
707
en_US
ethz.pages.end
724
en_US
ethz.size
18 p.
en_US
ethz.version.deposit
acceptedVersion
en_US
ethz.event
15th European Conference on Computer Vision (ECCV 2018)
en_US
ethz.event.location
Munich, Germany
en_US
ethz.event.date
September 8-14, 2018
en_US
ethz.publication.place
Cham
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::01209 - Lehre Inf.technologie u. Elektrotechnik
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::03514 - Van Gool, Luc / Van Gool, Luc
ethz.date.deposited
2018-11-22T18:06:56Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Embargoed
en_US
ethz.date.embargoend
2019-10-06
ethz.rosetta.installDate
2018-11-23T07:39:02Z
ethz.rosetta.lastUpdated
2019-01-03T09:39:47Z
ethz.rosetta.exportRequired
true
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Model%20Adaptation%20with%20Synthetic%20and%20Real%20Data%20for%20Semantic%20Dense%20Foggy%20Scene%20Understanding&rft.jtitle=Lecture%20Notes%20in%20Computer%20Science&rft.date=2018&rft.volume=11217&rft.spage=707&rft.epage=724&rft.issn=0302-9743&1611-3349&rft.au=Sakaridis,%20Christos&Dai,%20Dengxin&Hecker,%20Simon&Van%20Gool,%20Luc&rft.isbn=978-3-030-01260-1&978-3-030-01261-8&rft.genre=proceeding&rft_id=info:doi/978-3-030-01260-1&info:doi/978-3-030-01261-8&rft.btitle=Computer%20Vision%20%E2%80%93%20ECCV%202018%2015th%20European%20Conference,%20Munich,%20Germany,%20September%208-14,%202018,%20Proceedings,%20Part%20XIII
 Suchen via SFX

Dateien zu diesem Eintrag

Thumbnail

Publikationstyp

Zur Kurzanzeige