Show simple item record

dc.contributor.author
Yang, Ren
dc.contributor.author
Mentzer, Fabian
dc.contributor.author
Van Gool, Luc
dc.contributor.author
Timofte, Radu
dc.date.accessioned
2021-03-05T13:21:07Z
dc.date.available
2021-01-08T09:10:48Z
dc.date.available
2021-01-08T09:40:29Z
dc.date.available
2021-03-05T13:21:07Z
dc.date.issued
2021-02
dc.identifier.issn
1932-4553
dc.identifier.issn
1941-0484
dc.identifier.other
10.1109/jstsp.2020.3043590
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/460504
dc.description.abstract
The past few years have witnessed increasing interests in applying deep learning to video compression. However, the existing approaches compress a video frame with only a few number of reference frames, which limits their ability to fully exploit the temporal correlation among video frames. To overcome this shortcoming, this paper proposes a Recurrent Learned Video Compression (RLVC) approach with the Recurrent Auto-Encoder (RAE) and Recurrent Probability Model (RPM). Specifically, the RAE employs recurrent cells in both the encoder and decoder. As such, the temporal information in a large range of frames can be used for generating latent representations and reconstructing compressed outputs. Furthermore, the proposed RPM network recurrently estimates the Probability Mass Function (PMF) of the latent representation, conditioned on the distribution of previous latent representations. Due to the correlation among consecutive frames, the conditional cross entropy can be lower than the independent cross entropy, thus reducing the bit-rate. The experiments show that the our approach achieves the state-of-the-art learned video compression performance in terms of both PSNR and MS-SSIM. Moreover, our approach outperforms the default Low-Delay P (LDP) setting of x265 on PSNR, and also has better performance on MS-SSIM than the SSIM-tuned x265 and the slowest setting of x265.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.title
Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model
en_US
dc.type
Journal Article
dc.date.published
2020-12-09
ethz.journal.title
IEEE Journal of Selected Topics in Signal Processing
ethz.journal.volume
15
en_US
ethz.journal.issue
2
en_US
ethz.pages.start
388
en_US
ethz.pages.end
401
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
New York, NY
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
2021-01-08T09:10:55Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-03-05T13:21:17Z
ethz.rosetta.lastUpdated
2021-03-05T13:21:17Z
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=Learning%20for%20Video%20Compression%20with%20Recurrent%20Auto-Encoder%20and%20Recurrent%20Probability%20Model&rft.jtitle=IEEE%20Journal%20of%20Selected%20Topics%20in%20Signal%20Processing&rft.date=2021-02&rft.volume=15&rft.issue=2&rft.spage=388&rft.epage=401&rft.issn=1932-4553&1941-0484&rft.au=Yang,%20Ren&Mentzer,%20Fabian&Van%20Gool,%20Luc&Timofte,%20Radu&rft.genre=article&rft_id=info:doi/10.1109/jstsp.2020.3043590&
 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