Show simple item record

dc.contributor.author
Liang, Jingyun
dc.contributor.author
Lugmayr, Andreas
dc.contributor.author
Zhang, Kai
dc.contributor.author
Danelljan, Martin
dc.contributor.author
Van Gool, Luc
dc.contributor.author
Timofte, Radu
dc.date.accessioned
2022-06-30T08:58:52Z
dc.date.available
2021-12-02T15:05:24Z
dc.date.available
2022-06-21T12:36:13Z
dc.date.available
2022-06-21T12:53:23Z
dc.date.available
2022-06-30T08:58:52Z
dc.date.issued
2021
dc.identifier.isbn
978-1-6654-2812-5
en_US
dc.identifier.isbn
978-1-6654-2813-2
en_US
dc.identifier.other
10.1109/ICCV48922.2021.00404
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/518291
dc.description.abstract
Normalizing flows have recently demonstrated promising results for low-level vision tasks. For image super-resolution (SR), it learns to predict diverse photo-realistic high-resolution (HR) images from the low-resolution (LR) image rather than learning a deterministic mapping. For image rescaling, it achieves high accuracy by jointly modelling the downscaling and upscaling processes. While existing approaches employ specialized techniques for these two tasks, we set out to unify them in a single formulation. In this paper, we propose the hierarchical conditional flow (HCFlow) as a unified framework for image SR and image rescaling. More specifically, HCFlow learns a bijective mapping between HR and LR image pairs by modelling the distribution of the LR image and the rest high-frequency component simultaneously. In particular, the high-frequency component is conditional on the LR image in a hierarchical manner. To further enhance the performance, other losses such as perceptual loss and GAN loss are combined with the commonly used negative log-likelihood loss in training. Extensive experiments on general image SR, face image SR and image rescaling have demonstrated that the proposed HCFlow achieves state-of-the-art performance in terms of both quantitative metrics and visual quality.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.subject
Low-level and physics-based vision
en_US
dc.title
Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
en_US
dc.type
Conference Paper
dc.date.published
2022-02-28
ethz.book.title
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
en_US
ethz.pages.start
4076
en_US
ethz.pages.end
4085
en_US
ethz.event
18th International Conference on Computer Vision (ICCV 2021)
en_US
ethz.event.location
Online
ethz.event.date
October 11-17, 2021
en_US
ethz.identifier.wos
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
en_US
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
en_US
ethz.date.deposited
2021-11-30T11:25:58Z
ethz.source
BATCH
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2022-06-21T12:36:22Z
ethz.rosetta.lastUpdated
2023-02-07T03:54:04Z
ethz.rosetta.versionExported
true
dc.identifier.olduri
http://hdl.handle.net/20.500.11850/517786
dc.identifier.olduri
http://hdl.handle.net/20.500.11850/517780
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Hierarchical%20Conditional%20Flow:%20A%20Unified%20Framework%20for%20Image%20Super-Resolution%20and%20Image%20Rescaling&rft.date=2021&rft.spage=4076&rft.epage=4085&rft.au=Liang,%20Jingyun&Lugmayr,%20Andreas&Zhang,%20Kai&Danelljan,%20Martin&Van%20Gool,%20Luc&rft.isbn=978-1-6654-2812-5&978-1-6654-2813-2&rft.genre=proceeding&rft_id=info:doi/10.1109/ICCV48922.2021.00404&rft.btitle=2021%20IEEE/CVF%20International%20Conference%20on%20Computer%20Vision%20(ICCV)
 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