CAESR: Conditional Autoencoder and Super-Resolution for Learned Spatial Scalability

In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our framework considers a low-resolution signal encoded with VVC intra-mode as a base-layer (BL), and a deep conditional autoencoder with hyperprior (...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Visual communications and image processing (Online) S. 1 - 5
Hauptverfasser: Bonnineau, Charles, Hamidouche, Wassim, Travers, Jean-Francois, Sidaty, Naty, Aubie, Jean-Yves, Deforges, Olivier
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 05.12.2021
Schlagworte:
ISSN:2642-9357
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our framework considers a low-resolution signal encoded with VVC intra-mode as a base-layer (BL), and a deep conditional autoencoder with hyperprior (AE-HP) as an enhancement-layer (EL) model. The EL encoder takes as inputs both the upscaled BL reconstruction and the original image. Our approach relies on conditional coding that learns the optimal mixture of the source and the upscaled BL image, enabling better performance than residual coding. On the decoder side, a super-resolution (SR) module is used to recover high-resolution details and invert the conditional coding process. Experimental results have shown that our solution is competitive with the VVC full-resolution intra coding while being scalable.
AbstractList In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our framework considers a low-resolution signal encoded with VVC intra-mode as a base-layer (BL), and a deep conditional autoencoder with hyperprior (AE-HP) as an enhancement-layer (EL) model. The EL encoder takes as inputs both the upscaled BL reconstruction and the original image. Our approach relies on conditional coding that learns the optimal mixture of the source and the upscaled BL image, enabling better performance than residual coding. On the decoder side, a super-resolution (SR) module is used to recover high-resolution details and invert the conditional coding process. Experimental results have shown that our solution is competitive with the VVC full-resolution intra coding while being scalable.
Author Bonnineau, Charles
Hamidouche, Wassim
Deforges, Olivier
Travers, Jean-Francois
Sidaty, Naty
Aubie, Jean-Yves
Author_xml – sequence: 1
  givenname: Charles
  surname: Bonnineau
  fullname: Bonnineau, Charles
  organization: IRT b<>com,Cesson-Sevigne,France
– sequence: 2
  givenname: Wassim
  surname: Hamidouche
  fullname: Hamidouche, Wassim
  organization: IRT b<>com,Cesson-Sevigne,France
– sequence: 3
  givenname: Jean-Francois
  surname: Travers
  fullname: Travers, Jean-Francois
  organization: TDF,Cesson-Sevigne,France
– sequence: 4
  givenname: Naty
  surname: Sidaty
  fullname: Sidaty, Naty
  organization: TDF,Cesson-Sevigne,France
– sequence: 5
  givenname: Jean-Yves
  surname: Aubie
  fullname: Aubie, Jean-Yves
  organization: IRT b<>com,Cesson-Sevigne,France
– sequence: 6
  givenname: Olivier
  surname: Deforges
  fullname: Deforges, Olivier
  organization: Univ Rennes, INSA Rennes, CNRS, IETR - UMR 6164,Rennes,France
BookMark eNotkMFOwzAQRA0Cibb0C5BQfiDFXju1za2KClSqBGqAa7W2N8IoxFGSHvr3FNHTHN68OcyUXbWpJcbuBV8Iwe3DZ7l5KyQoWAAHsbBLXchCXLCp0GCEKQohL9kElgpyKwt9w-bD8M05hxMAayasKlfraveYlakNcYypxSZbHcZErU-B-gzbkFWHjvp8R0NqDn-VrE59tiXsWzrBDsd4kiqPDbrYxPF4y65rbAaan3PGPp7W7-VLvn193pSrbf4FUo-5884GodH4sPRShFA77kkCcGGV4UYrrD2aWiM4TuDACmXIoENVI0klZ-zufzcS0b7r4w_2x_35A_kLlHJT1A
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/VCIP53242.2021.9675351
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
Accès Toulouse INP et ENVT - IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Xplore Digital Library
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 1728185513
9781728185514
EISSN 2642-9357
EndPage 5
ExternalDocumentID 9675351
Genre orig-research
GroupedDBID 6IE
6IF
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
M43
OCL
RIE
RIL
ID FETCH-LOGICAL-h237t-bcb9d17a8cd6c31ddfb0ce322019480874afca8f7a2b0e2b29148e8aba4fae343
IEDL.DBID RIE
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000768800300037&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:25:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-h237t-bcb9d17a8cd6c31ddfb0ce322019480874afca8f7a2b0e2b29148e8aba4fae343
PageCount 5
ParticipantIDs ieee_primary_9675351
PublicationCentury 2000
PublicationDate 2021-Dec.-5
PublicationDateYYYYMMDD 2021-12-05
PublicationDate_xml – month: 12
  year: 2021
  text: 2021-Dec.-5
  day: 05
PublicationDecade 2020
PublicationTitle Visual communications and image processing (Online)
PublicationTitleAbbrev VCIP
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002513298
Score 2.1797285
Snippet In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Conditional Autoencoder
Encoding
Image coding
Scalability
Spatial Scalability
Super-Resolution
Superresolution
Training
Video coding
Visual communication
VVC
Title CAESR: Conditional Autoencoder and Super-Resolution for Learned Spatial Scalability
URI https://ieeexplore.ieee.org/document/9675351
WOSCitedRecordID wos000768800300037&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8NAEF1q8eCpait-swePpk2y2-yut1JaFKQUq9Jbmd2dYC9pSRPBf-9uEiqCF28hZBKYyWbeTOa9JeSOQQTDBGSACiDgwCDQ4NaVBvdNxMiLBVYirs9iNpPLpZq3yP2eC4OI1fAZ9v1h9S_fbkzpW2UD5dAt83zpAyGSmqu176e4PM1iJRsScBSqwfv4aT70eMFVgXHUb4x_7aJSJZFp53-PPya9HzYene_zzAlpYXZKOg18pM3i3HXJYjyaLF4eqDOz67rFR0dlsfFSlRZzCpm7utxiHvieff3GUYdZaaWx6m_lp6ud0cLFrZbv_uqRt-nkdfwYNHsmBB8xE0WgjVY2EiCNTQyLrE11aNA53EE5LkMpOKQGZCog1iHGOlauHkIJGngKyDg7I-1sk-E5oUqElluTSEDLNUolGWjJjFLWhK4QuSBd76PVtpbFWDXuufz79BU58mGoJkGG16Rd5CXekEPzWax3-W0Vy2_D4aEi
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8JAEN0QNNETKhi_7cGjhba7pbveCIFAREIEDTcyuzuNXAoprYn_3t22wZh48dY0naaZ6XbeTOe9JeSBgg9hF7iLAsBlQMGVYNaVBPNNRN-KBRYirpNoOuXLpZjVyOOeC4OIxfAZtu1h8S9fb1RuW2UdYdAttXzpg5CxwCvZWvuOisnUNBC8ogH7nui898ez0CIGUwcGfrsy_7WPSpFGho3_PcAJaf3w8ZzZPtOckhomZ6RRAUinWp67Jpn3e4P565NjzPS6bPI5vTzbWLFKjakDibk632Lq2q59-c45BrU6hcqqvZWdrzZGcxO5UsD7q0XehoNFf-RWuya4HwGNMlcqKbQfAVe6q6ivdSw9hcblBswx7vGIQayAxxEE0sNABsJURMhBAosBKaPnpJ5sErwgjog8zbTqckDNJHLBKUhOlRBaeaYUuSRN66PVthTGWFXuufr79D05Gi1eJqvJePp8TY5tSIq5kPCG1LM0x1tyqD6z9S69K-L6DVNupGk
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=proceeding&rft.title=Visual+communications+and+image+processing+%28Online%29&rft.atitle=CAESR%3A+Conditional+Autoencoder+and+Super-Resolution+for+Learned+Spatial+Scalability&rft.au=Bonnineau%2C+Charles&rft.au=Hamidouche%2C+Wassim&rft.au=Travers%2C+Jean-Francois&rft.au=Sidaty%2C+Naty&rft.date=2021-12-05&rft.pub=IEEE&rft.eissn=2642-9357&rft.spage=1&rft.epage=5&rft_id=info:doi/10.1109%2FVCIP53242.2021.9675351&rft.externalDocID=9675351