Show simple item record

dc.contributor.author
Ignatov, Andrey
dc.contributor.author
Patel, Jagruti
dc.contributor.author
Timofte, Radu
dc.date.accessioned
2020-09-10T13:42:18Z
dc.date.available
2020-09-10T05:43:45Z
dc.date.available
2020-09-10T13:42:18Z
dc.date.issued
2020
dc.identifier.isbn
978-1-7281-9360-1
en_US
dc.identifier.isbn
978-1-7281-9361-8
en_US
dc.identifier.issn
21607516
dc.identifier.other
10.1109/CVPRW50498.2020.00217
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/439467
dc.description.abstract
Bokeh is an important artistic effect used to highlight the main object of interest on the photo by blurring all out-of-focus areas. While DSLR and system camera lenses can render this effect naturally, mobile cameras are unable to produce shallow depth-of-field photos due to a very small aperture diameter of their optics. Unlike the current solutions simulating bokeh by applying Gaussian blur to image background, in this paper we propose to learn a realistic shallow focus technique directly from the photos produced by DSLR cameras. For this, we present a large-scale bokeh dataset consisting of 5K shallow / wide depth-of-field image pairs captured using the Canon 7D DSLR with 50mm f/1.8 lenses. We use these images to train a deep learning model to reproduce a natural bokeh effect based on a single narrow-aperture image. The experimental results show that the proposed approach is able to render a plausible non-uniform bokeh even in case of complex input data with multiple objects. The dataset, pre-trained models and codes used in this paper are available on the project website: https://people.ee.ethz.ch/ ihnatova/pynet-bokeh.html. © 2020 IEEE.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.title
Rendering Natural Camera Bokeh Effect with Deep Learning
en_US
dc.type
Conference Paper
dc.date.published
2020-07-28
ethz.book.title
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
en_US
ethz.pages.start
1676
en_US
ethz.pages.end
1686
en_US
ethz.event
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2020) (virtual)
en_US
ethz.event.location
Seattle, WA, USA
en_US
ethz.event.date
June 14-19, 2020
en_US
ethz.identifier.scopus
ethz.publication.place
Piscataway, NJ
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::03514 - Van Gool, Luc / Van Gool, Luc
ethz.leitzahl.certified
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
2020-09-10T05:44:24Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2020-09-10T13:42:32Z
ethz.rosetta.lastUpdated
2021-02-15T17:09:11Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Rendering%20Natural%20Camera%20Bokeh%20Effect%20with%20Deep%20Learning&rft.date=2020&rft.spage=1676&rft.epage=1686&rft.issn=21607516&rft.au=Ignatov,%20Andrey&Patel,%20Jagruti&Timofte,%20Radu&rft.isbn=978-1-7281-9360-1&978-1-7281-9361-8&rft.genre=proceeding&rft_id=info:doi/10.1109/CVPRW50498.2020.00217&rft.btitle=2020%20IEEE/CVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20(CVPRW)
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record