Semantics-Guided Diffusion for Deep Joint Source-Channel Coding in Wireless Image Transmission

Joint source-channel coding (JSCC) offers a promising avenue for enhancing transmission efficiency by jointly incorporating source and channel statistics into the system design. A key advancement in this area is the deep joint source and channel coding (DeepJSCC) technique that designs a direct mapp...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on wireless communications p. 1
Main Authors: Zhang, Maojun, Wu, Haotian, Zhu, Guangxu, Jin, Richeng, Chen, Xiaoming, Gunduz, Deniz
Format: Journal Article
Language:English
Published: IEEE 2025
Subjects:
Accuracy
Channel estimation
Data models
Fading channels
Image coding
Image reconstruction
joint source-channel coding
Noise reduction
Receivers
Semantics
semantics-guided diffusion models
Wireless communication
wireless image transmission
ISSN:1536-1276, 1558-2248
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Joint source-channel coding (JSCC) offers a promising avenue for enhancing transmission efficiency by jointly incorporating source and channel statistics into the system design. A key advancement in this area is the deep joint source and channel coding (DeepJSCC) technique that designs a direct mapping of input signals to channel symbols parameterized by a neural network, which can be trained for arbitrary channel models and semantic quality metrics. This paper advances the DeepJSCC framework toward a semantics-aligned, high-fidelity transmission approach, called semantics-guided diffusion DeepJSCC (SGD-JSCC). Existing schemes that integrate diffusion models (DMs) with JSCC face challenges in transforming random generation into accurate reconstruction and adapting to varying channel conditions. SGD-JSCC incorporates two key innovations: (1) utilizing some inherent information that contributes to the semantics of an image, such as text description or edge map, to guide the diffusion denoising process; and (2) enabling seamless adaptability to varying channel conditions with the help of a semantics-guided DM for channel denoising. The DM is guided by diverse semantic information and integrates seamlessly with DeepJSCC. In a slow fading channel, SGD-JSCC dynamically adapts to the instantaneous channel state information (CSI) directly estimated from the channel output, thereby eliminating the need for additional pilot transmissions for channel estimation. In a fast fading channel, we introduce a training-free denoising strategy, allowing SGD-JSCC to effectively adjust to fluctuations in channel gains. Numerical results demonstrate that, guided by semantic information and leveraging the powerful DM, our method outperforms existing DeepJSCC schemes, delivering satisfactory reconstruction performance even at extremely poor channel conditions. The proposed scheme highlights the potential of incorporating diffusion models in future communication systems. The code and pretrained checkpoints will be publicly available at https://github.com/MauroZMJ/SGDJSCC, allowing integration of this scheme with existing DeepJSCC models, without the need for retraining from scratch.
AbstractList Joint source-channel coding (JSCC) offers a promising avenue for enhancing transmission efficiency by jointly incorporating source and channel statistics into the system design. A key advancement in this area is the deep joint source and channel coding (DeepJSCC) technique that designs a direct mapping of input signals to channel symbols parameterized by a neural network, which can be trained for arbitrary channel models and semantic quality metrics. This paper advances the DeepJSCC framework toward a semantics-aligned, high-fidelity transmission approach, called semantics-guided diffusion DeepJSCC (SGD-JSCC). Existing schemes that integrate diffusion models (DMs) with JSCC face challenges in transforming random generation into accurate reconstruction and adapting to varying channel conditions. SGD-JSCC incorporates two key innovations: (1) utilizing some inherent information that contributes to the semantics of an image, such as text description or edge map, to guide the diffusion denoising process; and (2) enabling seamless adaptability to varying channel conditions with the help of a semantics-guided DM for channel denoising. The DM is guided by diverse semantic information and integrates seamlessly with DeepJSCC. In a slow fading channel, SGD-JSCC dynamically adapts to the instantaneous channel state information (CSI) directly estimated from the channel output, thereby eliminating the need for additional pilot transmissions for channel estimation. In a fast fading channel, we introduce a training-free denoising strategy, allowing SGD-JSCC to effectively adjust to fluctuations in channel gains. Numerical results demonstrate that, guided by semantic information and leveraging the powerful DM, our method outperforms existing DeepJSCC schemes, delivering satisfactory reconstruction performance even at extremely poor channel conditions. The proposed scheme highlights the potential of incorporating diffusion models in future communication systems. The code and pretrained checkpoints will be publicly available at https://github.com/MauroZMJ/SGDJSCC, allowing integration of this scheme with existing DeepJSCC models, without the need for retraining from scratch.
Author Jin, Richeng
Zhu, Guangxu
Gunduz, Deniz
Zhang, Maojun
Wu, Haotian
Chen, Xiaoming
Author_xml – sequence: 1
  givenname: Maojun
  orcidid: 0009-0005-7649-9260
  surname: Zhang
  fullname: Zhang, Maojun
  email: zhmj@zju.edu.cn
  organization: College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
– sequence: 2
  givenname: Haotian
  orcidid: 0000-0003-2137-6907
  surname: Wu
  fullname: Wu, Haotian
  email: haotian.wu17@imperial.ac.uk
  organization: Department of Electrical and Electronic Engineering, Imperial College London, United Kingdom
– sequence: 3
  givenname: Guangxu
  orcidid: 0000-0001-9532-9201
  surname: Zhu
  fullname: Zhu, Guangxu
  email: gxzhu@sribd.cn
  organization: Shenzhen Research Institute of Big Data, Shenzhen, China
– sequence: 4
  givenname: Richeng
  orcidid: 0000-0002-1480-585X
  surname: Jin
  fullname: Jin, Richeng
  email: richengjin@zju.edu.cn
  organization: Department of Information and Communication Engineering, Zhejiang University, China
– sequence: 5
  givenname: Xiaoming
  orcidid: 0000-0002-1818-2135
  surname: Chen
  fullname: Chen, Xiaoming
  email: chen_xiaoming@zju.edu.cn
  organization: College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
– sequence: 6
  givenname: Deniz
  orcidid: 0000-0002-7725-395X
  surname: Gunduz
  fullname: Gunduz, Deniz
  email: d.gunduz@imperial.ac.uk
  organization: Department of Electrical and Electronic Engineering, Imperial College London, United Kingdom
BookMark eNpFkD1PwzAYhC1UJNrCzsDgP5Diz8QZUQoFVImhRd2IXPt1MWrsym4H_j2JWgndcDfc3fBM0CjEAAjdUzKjlNSP600zY4TJGZc1FbK8QmMqpSoYE2o0ZF4WlFXlDZrk_EMIrUopx-hrBZ0OR29ysTh5CxbPvXOn7GPALiY8Bzjg9-jDEa_iKRkomm8dAuxxE60PO-wD3vgEe8gZv3V6B3iddMidz8PHLbp2ep_h7uJT9PnyvG5ei-XH4q15WhaGcnEstDO2UqKswDojhIBeVlIwTDliy9puNak4k9ZsXe2YMHUpGKFEVluulAQ-ReT8a1LMOYFrD8l3Ov22lLQDn7bn0w582guffvJwnngA-K_33Vqqmv8BS71kaQ
CODEN ITWCAX
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/TWC.2025.3591456
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE/IET Electronic Library (IEL)
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-2248
EndPage 1
ExternalDocumentID 10_1109_TWC_2025_3591456
11099589
Genre orig-research
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
HZ~
IES
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
AAYXX
AETIX
AIBXA
CITATION
EJD
H~9
ID FETCH-LOGICAL-c134t-afcd78467edfc444e4e4d51ec28f0d69dba07325dcbf9f24c964201057b3885e3
IEDL.DBID RIE
ISSN 1536-1276
IngestDate Sat Nov 29 07:39:10 EST 2025
Wed Aug 06 17:59:57 EDT 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c134t-afcd78467edfc444e4e4d51ec28f0d69dba07325dcbf9f24c964201057b3885e3
ORCID 0000-0003-2137-6907
0000-0002-1818-2135
0000-0002-1480-585X
0000-0001-9532-9201
0009-0005-7649-9260
0000-0002-7725-395X
PageCount 1
ParticipantIDs crossref_primary_10_1109_TWC_2025_3591456
ieee_primary_11099589
PublicationCentury 2000
PublicationDate 2025-00-00
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 2025-00-00
PublicationDecade 2020
PublicationTitle IEEE transactions on wireless communications
PublicationTitleAbbrev TWC
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0017655
Score 2.5204222
Snippet Joint source-channel coding (JSCC) offers a promising avenue for enhancing transmission efficiency by jointly incorporating source and channel statistics into...
SourceID crossref
ieee
SourceType Index Database
Publisher
StartPage 1
SubjectTerms Accuracy
Channel estimation
Data models
Fading channels
Image coding
Image reconstruction
joint source-channel coding
Noise reduction
Receivers
Semantics
semantics-guided diffusion models
Wireless communication
wireless image transmission
Title Semantics-Guided Diffusion for Deep Joint Source-Channel Coding in Wireless Image Transmission
URI https://ieeexplore.ieee.org/document/11099589
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-2248
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017655
  issn: 1536-1276
  databaseCode: RIE
  dateStart: 20020101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZoxQADzyLKSx5YGNI2idPYI2opD6EKqUV0Imp8ZylSm1Z98PvxOaF0YUBZosiJojvb3z189zF2K6NUEHR4oHxNDgp4aRihhzLQ0PI1iKJJ0mvc78vRSL2VxequFgYR3eEzbNCty-XDTK8pVNak7pgqkqrCKnHcLoq1NimDuO0oTu0KJmKZeJOTbKnm8KNjPcEgaoSR8gVxVW9h0BapisOU3uE__-aIHZTGI78vtH3MdjA_YftbLQVP2ecAp1ZYmV56j-sMEHg3M2ZNMTFu7VPeRZzzl1mWr_jAxe09qi_IccI7M4IxnuWcTsRO7A7In6d2t-EOzux0oG_U2HvvYdh58koOBU_7oVh5Y6MhJhsDwWghBNoLIh91IE0L2grSsV3kQQQ6NcoEQivrkBBrZpyGUkYYnrFqPsvxnHEA8JVOxxqCVMRGSqOlMu1AQjiWwqR1dvcj1WRetMpInIvRUonVQEIaSEoN1FmNBPo7rpTlxR_PL9kevV7EPq5YdbVY4zXb1V-rbLm4cRPhG3uTsqA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagIAEDb0R5emBhCORhN_aIyptSIVEEE1HjO0uRaFpBy-_H5wTowoCyRJFlRXe2v3v47mPsSMlcEHQEoCNDDgoEeSIxQBUbCCMDomqS1Em7XfXyoh_qYnVfC4OI_vIZntCrz-XD0EwoVHZK3TG1VHqWzUkh4rAq1_pJGqQtT3Lq9jBRy6Q_WclQn_ae284XjOVJInUkiK16CoWmaFU8qlyu_PN_VtlybT7ys0rfa2wGy3W2NNVUcIO9PuLAiaswH8HVpAAEfl5YO6GoGHcWKj9HHPHbYVGO-aOP3AdUYVDiG28PCch4UXK6E_vmzkB-M3DnDfeA5hYEzbHJni4veu3roGZRCEyUiHHQtwZSsjIQrBFCoHtARmhiZUNoacj7bpvHEkxutY2F0c4lId7MNE-UkphssUY5LHGbcQCItMn7BuJcpFYpa5S2rVhB0lfC5k12_C3VbFQ1y8i8kxHqzGkgIw1ktQaabJME-juuluXOH98P2cJ1776TdW66d7tskaaqIiF7rDF-n-A-mzef4-Lj_cAvii_zO7Xn
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=article&rft.atitle=Semantics-Guided+Diffusion+for+Deep+Joint+Source-Channel+Coding+in+Wireless+Image+Transmission&rft.jtitle=IEEE+transactions+on+wireless+communications&rft.au=Zhang%2C+Maojun&rft.au=Wu%2C+Haotian&rft.au=Zhu%2C+Guangxu&rft.au=Jin%2C+Richeng&rft.date=2025&rft.issn=1536-1276&rft.eissn=1558-2248&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FTWC.2025.3591456&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TWC_2025_3591456
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1536-1276&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1536-1276&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1536-1276&client=summon