BBDM: Image-to-Image Translation with Brownian Bridge Diffusion Models

Image-to-image translation is an important and challenging problem in computer vision and image processing. Diffusion models (DM) have shown great potentials for high-quality image synthesis, and have gained competitive performance on the task of image-to-image translation. However, most of the exis...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 1952 - 1961
Main Authors: Li, Bo, Xue, Kaitao, Liu, Bin, Lai, Yu-Kun
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2023
Subjects:
Bridges
Computational modeling
Computer vision
Diffusion processes
Image and video synthesis and generation
Measurement
Stochastic processes
Visualization
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Image-to-image translation is an important and challenging problem in computer vision and image processing. Diffusion models (DM) have shown great potentials for high-quality image synthesis, and have gained competitive performance on the task of image-to-image translation. However, most of the existing diffusion models treat image-to-image translation as conditional generation processes, and suffer heavily from the gap between distinct domains. In this paper, a novel image-to-image translation method based on the Brownian Bridge Diffusion Model (BBDM) is proposed, which models image-to-image translation as a stochastic Brownian Bridge process, and learns the translation between two domains directly through the bidirectional diffusion process rather than a conditional generation process. To the best of our knowledge, it is the first work that proposes Brownian Bridge diffusion process for image-to-image translation. Experimental results on various benchmarks demonstrate that the proposed BBDM model achieves competitive performance through both visual inspection and measurable metrics.
AbstractList Image-to-image translation is an important and challenging problem in computer vision and image processing. Diffusion models (DM) have shown great potentials for high-quality image synthesis, and have gained competitive performance on the task of image-to-image translation. However, most of the existing diffusion models treat image-to-image translation as conditional generation processes, and suffer heavily from the gap between distinct domains. In this paper, a novel image-to-image translation method based on the Brownian Bridge Diffusion Model (BBDM) is proposed, which models image-to-image translation as a stochastic Brownian Bridge process, and learns the translation between two domains directly through the bidirectional diffusion process rather than a conditional generation process. To the best of our knowledge, it is the first work that proposes Brownian Bridge diffusion process for image-to-image translation. Experimental results on various benchmarks demonstrate that the proposed BBDM model achieves competitive performance through both visual inspection and measurable metrics.
Author Lai, Yu-Kun
Liu, Bin
Li, Bo
Xue, Kaitao
Author_xml – sequence: 1
  givenname: Bo
  surname: Li
  fullname: Li, Bo
  organization: School of Mathematics and Information Science, Nanchang Hangkong University,Nanchang,China
– sequence: 2
  givenname: Kaitao
  surname: Xue
  fullname: Xue, Kaitao
  organization: School of Mathematics and Information Science, Nanchang Hangkong University,Nanchang,China
– sequence: 3
  givenname: Bin
  surname: Liu
  fullname: Liu, Bin
  organization: School of Mathematics and Information Science, Nanchang Hangkong University,Nanchang,China
– sequence: 4
  givenname: Yu-Kun
  surname: Lai
  fullname: Lai, Yu-Kun
  organization: School of Computer Sciences and Informatics, Cardiff University,Cardiff,UK
BookMark eNotjMtOwzAQRQ0CiVLyB13kBxxmxnEcsyNpC5VagVBhW9mJA0apg5Kgir-nPFb3SOfoXrKz0AXH2AwhQQR9Xb48PklSpBMCEgkA6vSERVrpXEgQgKTzUzZByATPNOoLFg3DOwAIQsx0PmHLophvbuLV3rw6Pnb8F-Jtb8LQmtF3IT748S0u-u4QvAlH8PUxmPum-Rx-9KarXTtcsfPGtIOL_nfKnpeLbXnP1w93q_J2zT1BOvJGIlVQUW0dGS2JUqUqVCIXFRqlrLQNmrTJKTVSqbqWWWaEsKk0wlmrSUzZ7O_XO-d2H73fm_5rh0AgsqP-BqXwTao
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR52729.2023.00194
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 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 9798350301298
EISSN 1063-6919
EndPage 1961
ExternalDocumentID 10203692
Genre orig-research
GrantInformation_xml – fundername: Natural Science Foundation of China (NSFC)
  grantid: 62172198,61762064
  funderid: 10.13039/501100001809
– fundername: Key Project of Jiangxi Natural Science Foundation
  grantid: 20224ACB202008
  funderid: 10.13039/501100004479
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i204t-f512c0c2dbe2a9522477c17383c1a77b5bf1a4f824a577dd566a33b45a3ebb923
IEDL.DBID RIE
ISICitedReferencesCount 119
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001058542602027&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 02:56:32 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i204t-f512c0c2dbe2a9522477c17383c1a77b5bf1a4f824a577dd566a33b45a3ebb923
PageCount 10
ParticipantIDs ieee_primary_10203692
PublicationCentury 2000
PublicationDate 2023-June
PublicationDateYYYYMMDD 2023-06-01
PublicationDate_xml – month: 06
  year: 2023
  text: 2023-June
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.631132
Snippet Image-to-image translation is an important and challenging problem in computer vision and image processing. Diffusion models (DM) have shown great potentials...
SourceID ieee
SourceType Publisher
StartPage 1952
SubjectTerms Bridges
Computational modeling
Computer vision
Diffusion processes
Image and video synthesis and generation
Measurement
Stochastic processes
Visualization
Title BBDM: Image-to-Image Translation with Brownian Bridge Diffusion Models
URI https://ieeexplore.ieee.org/document/10203692
WOSCitedRecordID wos001058542602027&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/eLvHCXMwlV07T8MwELagYmAqjyLe8sDq0sR2HDO2UMFAVSFA3So_pUrQojbl93PnhMLCwHbJEukc-757fP4IueJOR6mEZsFpzURpAjMxloyLACsuHLaGktiEGo3KyUSPG7J64sKEENLwWeiimXr5fuHWWCqDHY5tMw0n7rZSRU3W2hRUOKQyhS4belzW09eD1_GTzAE9dlEjHHsOKE38S0QlxZBh-59f3yOdHzYeHW_izD7ZCvMD0m7gI2025-qQDPv928cb-vAORwSrFiwZNAWjeuCNYtGVpsQbfgowkKtFb2cxrrFmRlEX7W3VIS_Du-fBPWtkEtgs74mKRYjZrudyb0NuNOApoZTLFKSeLjNKWWljZkQsc2GkUt4DgDOcWyEND9YCwDsirfliHo4J9fAkhLayUFFwH020WBjSvvCeS5ufkA76ZfpR34Qx_XbJ6R_vz8guur4erTonrWq5Dhdkx31Ws9XyMq3fFwYsmnI
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG4MmugJHxjf9uC1yG5buvUISCACIQYNN9JnQqJgYPH3O-2u6MWDt9m9bNLZdr55fP0QuqNGei6YJM5ISVimHFHeZ4QyBx5nJrSGotiEGI2y6VSOS7J65MI45-LwmasHM_by7dJsQqkMdnhom0k4cXc5g8SnoGttSyoUkpmmzEqCXNKQ9-3X8TNPAT_Wg0p46DoEceJfMioxinSr__z-Iar98PHweBtpjtCOWxyjagkgcbk91yeo22p1hg-4_w6HBMmXJBo4hqNi5A2HsiuOqTf8FmAEthbuzL3fhKoZDspob-saeuk-Tto9UgolkHnaYDnxELVNw6RWu1RJQFRMCJMISD5NooTQXPtEMZ-lTHEhrAUIpyjVjCvqtAaId4oqi-XCnSFs4YkxqXlTeEatV16H0pC0TWsp1-k5qoV1mX0Ud2HMvpfk4o_3t2i_NxkOZoP-6OkSHQQ3FINWV6iSrzbuGu2Zz3y-Xt1EX34BQSKduQ
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%3Abook&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=BBDM%3A+Image-to-Image+Translation+with+Brownian+Bridge+Diffusion+Models&rft.au=Li%2C+Bo&rft.au=Xue%2C+Kaitao&rft.au=Liu%2C+Bin&rft.au=Lai%2C+Yu-Kun&rft.date=2023-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=1952&rft.epage=1961&rft_id=info:doi/10.1109%2FCVPR52729.2023.00194&rft.externalDocID=10203692