MRFuse: Metric learning and masked autoencoder for fusing real infrared and visible images

The task of infrared and visible image fusion aims to retain the thermal targets from infrared images while preserving the details, brightness, and other important features from visible images. Current methods face challenges such as unclear fusion objectives, difficulty in interpreting the learning...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Optics and laser technology Jg. 189; S. 112971
Hauptverfasser: Li, YuBin, Zhan, Weida, Guo, Jinxin, Zhu, Depeng, Jiang, Yichun, Chen, Yu, Xu, Xiaoyu, Han, Deng
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.11.2025
Schlagworte:
ISSN:0030-3992
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The task of infrared and visible image fusion aims to retain the thermal targets from infrared images while preserving the details, brightness, and other important features from visible images. Current methods face challenges such as unclear fusion objectives, difficulty in interpreting the learning process, and uncontrollable auxiliary learning weights. To address these issues, this paper proposes a novel fusion method based on metric learning and masked autoencoders for real infrared and visible image fusion, termed MRFuse. MRFuse operates through a combination of metric mapping space, auxiliary networks, and fusion networks. First, we introduce a Real Degradation Estimation Module (RDEM), which employs a simple neural network to establish a controllable degradation estimation scheme within the metric space. Additionally, to train the metric space, we propose a sample generation method that provides complex training samples for the metric learning pipeline. Next, we present a fusion network based on masked autoencoding. Specifically, we construct hybrid masked infrared and visible image pairs and design a U-shaped ViT encoder–decoder architecture. This architecture leverages hierarchical feature representation and layer-wise fusion to reconstruct high-quality fused images. Finally, to train the fusion network, we design a masked region loss to constrain reconstruction errors within masked regions, and further employ gradient loss, structural consistency loss, and perceptual loss to enhance the quality of the fused images. Extensive experiments demonstrate that MRFuse exhibits superior controllability and excels in suppressing noise, blur, and glare, outperforming other state-of-the-art methods in both subjective and objective evaluations. •A new controllable and interpretable method for infrared and visible image fusion.•Metric space guides the fusion process.•New hybrid mask input method increases the robustness of the fusion network.•MAE networks with masking loss constraints produce superior fusion images.
AbstractList The task of infrared and visible image fusion aims to retain the thermal targets from infrared images while preserving the details, brightness, and other important features from visible images. Current methods face challenges such as unclear fusion objectives, difficulty in interpreting the learning process, and uncontrollable auxiliary learning weights. To address these issues, this paper proposes a novel fusion method based on metric learning and masked autoencoders for real infrared and visible image fusion, termed MRFuse. MRFuse operates through a combination of metric mapping space, auxiliary networks, and fusion networks. First, we introduce a Real Degradation Estimation Module (RDEM), which employs a simple neural network to establish a controllable degradation estimation scheme within the metric space. Additionally, to train the metric space, we propose a sample generation method that provides complex training samples for the metric learning pipeline. Next, we present a fusion network based on masked autoencoding. Specifically, we construct hybrid masked infrared and visible image pairs and design a U-shaped ViT encoder–decoder architecture. This architecture leverages hierarchical feature representation and layer-wise fusion to reconstruct high-quality fused images. Finally, to train the fusion network, we design a masked region loss to constrain reconstruction errors within masked regions, and further employ gradient loss, structural consistency loss, and perceptual loss to enhance the quality of the fused images. Extensive experiments demonstrate that MRFuse exhibits superior controllability and excels in suppressing noise, blur, and glare, outperforming other state-of-the-art methods in both subjective and objective evaluations. •A new controllable and interpretable method for infrared and visible image fusion.•Metric space guides the fusion process.•New hybrid mask input method increases the robustness of the fusion network.•MAE networks with masking loss constraints produce superior fusion images.
ArticleNumber 112971
Author Zhu, Depeng
Jiang, Yichun
Guo, Jinxin
Han, Deng
Zhan, Weida
Chen, Yu
Xu, Xiaoyu
Li, YuBin
Author_xml – sequence: 1
  givenname: YuBin
  surname: Li
  fullname: Li, YuBin
  email: lyb@mails.cust.edu.cn
  organization: Changchun University of Science and Technology National Demonstration Center for Experimental Electrical, 130000, Changchun, China
– sequence: 2
  givenname: Weida
  orcidid: 0000-0003-1011-7416
  surname: Zhan
  fullname: Zhan, Weida
  email: zhanweida@cust.edu.cn
  organization: Changchun University of Science and Technology National Demonstration Center for Experimental Electrical, 130000, Changchun, China
– sequence: 3
  givenname: Jinxin
  surname: Guo
  fullname: Guo, Jinxin
  email: guojinxin@mails.cust.edu.cn
  organization: Changchun University of Science and Technology National Demonstration Center for Experimental Electrical, 130000, Changchun, China
– sequence: 4
  givenname: Depeng
  surname: Zhu
  fullname: Zhu, Depeng
  email: zhudepeng@mails.cust.edu.cn
  organization: Changchun University of Science and Technology National Demonstration Center for Experimental Electrical, 130000, Changchun, China
– sequence: 5
  givenname: Yichun
  surname: Jiang
  fullname: Jiang, Yichun
  email: jiangyichun@cust.edu.cn
  organization: Changchun University of Science and Technology National Demonstration Center for Experimental Electrical, 130000, Changchun, China
– sequence: 6
  givenname: Yu
  surname: Chen
  fullname: Chen, Yu
  email: chenyu@mails.cust.edu.cn
  organization: Changchun University of Science and Technology National Demonstration Center for Experimental Electrical, 130000, Changchun, China
– sequence: 7
  givenname: Xiaoyu
  surname: Xu
  fullname: Xu, Xiaoyu
  email: cust-xxy@mails.cust.edu.cn
  organization: Changchun University of Science and Technology National Demonstration Center for Experimental Electrical, 130000, Changchun, China
– sequence: 8
  givenname: Deng
  surname: Han
  fullname: Han, Deng
  email: jl11269@buaa.edu.cn
  organization: Jilin Province Zhixing IoT Research Institute Co., Ltd, 130117, Changchun, China
BookMark eNqFkMFOwzAQRH0oEm3hG_APJNhxaifcqooCUiskBBcu1sZeVy5pXNlpJf6eREVcOazmMjOafTMy6UKHhNxxlnPG5f0-D8e-hdSjyQtWLHLOi1rxCZkyJlgm6rq4JrOU9oyxUi7ElHxu39anhA90i330hrYIsfPdjkJn6QHSF1oKpz5gZ4LFSF0Y7pRGR0Roqe9chDiaBv_ZJ9-0SP0BdphuyJWDNuHtr87Jx_rxffWcbV6fXlbLTWYKKfqsaQS3HERZl5K5Bh0KV1fOVGqhFC-hZAVIbq2rRaVANBJlBUoaa2xpneRiTtSl18SQUkSnj3FYEL81Z3rEovf6D4sesegLliG5vCRxmHf2GHUyfvgUrY9oem2D_7fjB3zwdXQ
Cites_doi 10.1007/s11263-023-01948-x
10.1007/s13042-023-01833-6
10.1016/j.inffus.2022.09.030
10.1016/j.inffus.2022.03.007
10.1109/ICCVW54120.2021.00389
10.1016/j.optcom.2024.131024
10.3390/app9061103
10.1109/TMM.2022.3228685
10.1016/j.inffus.2022.07.013
10.1109/TIM.2020.2986875
10.1016/j.infrared.2017.02.005
10.1016/j.dib.2017.09.038
10.1016/j.inffus.2021.02.023
10.1016/j.inffus.2022.09.019
10.1016/j.infrared.2022.104383
10.1109/TPAMI.2022.3221486
10.1016/j.inffus.2024.102841
10.1117/1.JEI.31.3.033043
10.1016/j.inffus.2019.07.005
10.3390/s18041169
10.1016/j.inffus.2022.11.010
10.1109/TMI.2019.2934577
10.1016/j.eswa.2024.123731
10.3934/ipi.2022075
10.1109/TASLP.2023.3349053
10.1109/TMM.2022.3192661
10.1016/j.inffus.2019.07.011
10.1364/AO.55.006480
10.3390/s17051127
10.1109/TCSVT.2023.3234340
10.1109/TCSVT.2021.3109895
10.1007/s11042-020-10035-z
10.1007/s00542-022-05315-7
10.1145/3503161.3547902
10.1109/CVPR52688.2022.00320
10.1364/OL.425485
10.1016/j.patcog.2024.110822
10.3390/electronics12071732
10.1016/j.inffus.2015.11.003
10.1016/j.inffus.2018.09.004
10.1016/j.infrared.2022.104486
10.3390/rs14122789
10.1016/j.infrared.2017.05.007
10.1109/TGRS.2023.3334729
10.3390/rs15030685
10.1016/j.cviu.2022.103407
10.1016/j.inffus.2022.10.034
10.1016/j.bspc.2022.104277
10.1109/TIP.2020.2977573
10.3390/s23020599
10.1109/TIP.2023.3263113
10.1016/j.compag.2022.107511
ContentType Journal Article
Copyright 2025 Elsevier Ltd
Copyright_xml – notice: 2025 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.optlastec.2025.112971
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Physics
ExternalDocumentID 10_1016_j_optlastec_2025_112971
S0030399225005626
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
123
1B1
1RT
1~.
1~5
29N
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABXZ
AAEDT
AAEDW
AAEPC
AAIKC
AAIKJ
AAKOC
AALRI
AAMNW
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYWO
ABDPE
ABJNI
ABMAC
ABNEU
ABWVN
ABXDB
ABXRA
ACBEA
ACDAQ
ACFVG
ACGFO
ACGFS
ACIWK
ACNNM
ACRLP
ACRPL
ACVFH
ADBBV
ADCNI
ADEZE
ADMUD
ADNMO
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AEUPX
AEZYN
AFFNX
AFJKZ
AFPUW
AFRZQ
AFTJW
AFXIZ
AGCQF
AGHFR
AGQPQ
AGRNS
AGUBO
AGYEJ
AHHHB
AHJVU
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AIVDX
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
APXCP
ASPBG
AVWKF
AXJTR
AZFZN
BBWZM
BJAXD
BKOJK
BLXMC
BNPGV
CS3
DU5
EBS
EFJIC
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
HMV
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LY7
M38
M41
MAGPM
MO0
N9A
NDZJH
O-L
O9-
OAUVE
OGIMB
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SDF
SDG
SDP
SES
SET
SEW
SPC
SPCBC
SPD
SPG
SSH
SSM
SSQ
SST
SSZ
T5K
TN5
UHS
WH7
WUQ
ZMT
~G-
9DU
AAYXX
ACLOT
CITATION
EFKBS
EFLBG
~HD
ID FETCH-LOGICAL-c263t-bb31d1a349460fbefe3f98fc8757714a402a61ddf9387a3b6e68a76cdcd4df613
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001508785100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0030-3992
IngestDate Sat Nov 29 07:48:38 EST 2025
Sat Jul 05 17:12:27 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Metric space
Masked autoencoder
Image degradation
Image fusion
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c263t-bb31d1a349460fbefe3f98fc8757714a402a61ddf9387a3b6e68a76cdcd4df613
ORCID 0000-0003-1011-7416
ParticipantIDs crossref_primary_10_1016_j_optlastec_2025_112971
elsevier_sciencedirect_doi_10_1016_j_optlastec_2025_112971
PublicationCentury 2000
PublicationDate November 2025
2025-11-00
PublicationDateYYYYMMDD 2025-11-01
PublicationDate_xml – month: 11
  year: 2025
  text: November 2025
PublicationDecade 2020
PublicationTitle Optics and laser technology
PublicationYear 2025
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Tang, Yuan, Zhang, Jiang, Ma (b60) 2022; 83
Bavirisetti, Xiao, Liu (b63) 2017
Wang, Shao, Chen, Xu, Zhang (b26) 2022; 25
Liu, Dou, Chen, Qin, Heng (b33) 2019; 39
Toet (b47) 2017; 15
Tang, He, Liu, Duan, Si (b31) 2023; 33
Karim, Tong, Li, Qadir, Farooq, Yu (b51) 2023; 90
Zhang, Liu, Sun, Yan, Zhao, Zhang (b67) 2020; 54
Yiming Sun, Bing Cao, Pengfei Zhu, Qinghua Hu, Detfusion: A detection-driven infrared and visible image fusion network, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 4003–4011.
Eymaël, Vandeghen, Cioppa, Giancola, Ghanem, Van Droogenbroeck (b44) 2024
Ma, Zhou, Wang, Zong (b64) 2017; 82
Kan, He, Cen, Li, Mladenovic, He (b39) 2022; 45
Tang, He, Liu (b30) 2022; 25
Wu, Liu, Sui, Cao (b70) 2021; 46
Li, Wu, Kittler (b10) 2018
Ma, Wang, Li, Yang, Li, Song, Li (b2) 2023; 23
Lin, Gao, Shi, Dong, Du (b40) 2023; 61
Singh, Singh, Gehlot, Kaur, Gagandeep (b7) 2023; 29
Xue, Wang, Zhao (b18) 2022; 127
Kim, Lee, Choi, Lee (b41) 2024
Gao, Liu, Yan (b19) 2020; 39
Zhang, Zhang (b53) 2023; 204
Patel, Chaudhary (b6) 2020
Li, Zhang, Hong, Yao, Chanussot (b12) 2023; 61
Fang, Zeng, Zhang, Liu, Zhao, Zhang, Yang, Liu, Miao, Hu (b37) 2023; 80
Wang, Wang, Wu, Xu, Zhang (b23) 2021; 32
Tang, Xiang, Zhang, Gong, Ma (b46) 2023; 91
Setiadi (b56) 2021; 80
Chen, Eickhoff (b35) 2021
Li, Kan, He (b38) 2020
Dong, Li, Li (b3) 2023; 12
Zhao, Xu, Zhang, Liu, Li, Zhang (b11) 2020
Li, Wu (b48) 2019; 9
Ma, Xu, Jiang, Mei, Zhang (b25) 2020; 29
Li, Hu, Ni, Zeng (b49) 2023; 17
Hong, Wu, Xu (b17) 2022; 31
Liu, Dian, Li, Liu (b28) 2023; 91
Liu, Liu, Wang, Du (b15) 2024; 573
Le, Huang, Xu, Fan, Ma, Mei, Ma (b66) 2022; 88
Li, Liu, Zhou, Zhang, Kasabov (b55) 2023; 128
Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick, Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16000–16009.
Ze Liu, Jia Ning, Yue Cao, Yixuan Wei, Zheng Zhang, Stephen Lin, Han Hu, Video swin transformer, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 3202–3211.
Jiang, Ren, Lin (b34) 2023
Weifeng Ge, Deep metric learning with hierarchical triplet loss, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 269–285.
Xu, Gong, Tian, Huang, Ma (b16) 2022; 218
Chang, Feng, Yang, Gao (b1) 2023; 32
(b58) 2017
Zuo, Liu, Bai, Wang, Sun (b20) 2017; 17
Huang, Bi, Wu (b21) 2018; 18
Guo, Zhan, Jiang, Ge, Chen, Xu, Li, Liu (b45) 2024; 249
Wang, Li, Zhang, Luo, Chen, Wang, Chi, Dai (b69) 2025; 117
Gao, Shi, Zhu, Fu, Wu (b4) 2022; 14
Ma, Yu, Liang, Li, Jiang (b24) 2019; 48
Wang, Xi, Li, Li (b29) 2023; 72
Huang, Li, Du, Shen (b14) 2024
Zhou, Wang, Li, Dong (b61) 2016; 30
Zhou, Dong, Xie, Gao (b62) 2016; 55
Cheng, Xu, Wu (b27) 2023; 92
Li, Wu, Kittler (b22) 2021; 73
Jiawei Ren, Mingyuan Zhang, Cunjun Yu, Ziwei Liu, Balanced mse for imbalanced visual regression, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7926–7935.
Li, Zou, Wang, Lin (b8) 2023; 15
Luo, Huang, Li, Wang, Tan (b50) 2022
Yang, Zhang, Huang, Zuo, Sun (b9) 2020; 70
Peng, Zhao, Hu, Zhuang, Wang (b5) 2023; 14
Ma, Liang, Yu, Chen, Guo, Wu, Jiang (b57) 2020; 54
Tang, He, Liu (b32) 2024; 156
Zhang, Zhang, Bai, Zhang (b65) 2017; 83
Li, Liu, Zhang, Liu (b13) 2024; 132
Gupta, Wu, Deng, Li (b43) 2023; 36
Xinyu Jia, Chuang Zhu, Minzhen Li, Wenqi Tang, Wenli Zhou, LLVIP: A visible-infrared paired dataset for low-light vision, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 3496–3504.
Ma (10.1016/j.optlastec.2025.112971_b57) 2020; 54
Tang (10.1016/j.optlastec.2025.112971_b32) 2024; 156
Singh (10.1016/j.optlastec.2025.112971_b7) 2023; 29
Gao (10.1016/j.optlastec.2025.112971_b4) 2022; 14
Li (10.1016/j.optlastec.2025.112971_b22) 2021; 73
Kim (10.1016/j.optlastec.2025.112971_b41) 2024
Le (10.1016/j.optlastec.2025.112971_b66) 2022; 88
Gupta (10.1016/j.optlastec.2025.112971_b43) 2023; 36
10.1016/j.optlastec.2025.112971_b42
Guo (10.1016/j.optlastec.2025.112971_b45) 2024; 249
Tang (10.1016/j.optlastec.2025.112971_b60) 2022; 83
Patel (10.1016/j.optlastec.2025.112971_b6) 2020
Jiang (10.1016/j.optlastec.2025.112971_b34) 2023
Zhang (10.1016/j.optlastec.2025.112971_b65) 2017; 83
Fang (10.1016/j.optlastec.2025.112971_b37) 2023; 80
Zhang (10.1016/j.optlastec.2025.112971_b53) 2023; 204
Zhou (10.1016/j.optlastec.2025.112971_b61) 2016; 30
Hong (10.1016/j.optlastec.2025.112971_b17) 2022; 31
Li (10.1016/j.optlastec.2025.112971_b12) 2023; 61
Kan (10.1016/j.optlastec.2025.112971_b39) 2022; 45
Li (10.1016/j.optlastec.2025.112971_b55) 2023; 128
Zhang (10.1016/j.optlastec.2025.112971_b67) 2020; 54
10.1016/j.optlastec.2025.112971_b54
Tang (10.1016/j.optlastec.2025.112971_b30) 2022; 25
Li (10.1016/j.optlastec.2025.112971_b48) 2019; 9
Li (10.1016/j.optlastec.2025.112971_b38) 2020
10.1016/j.optlastec.2025.112971_b59
Setiadi (10.1016/j.optlastec.2025.112971_b56) 2021; 80
Cheng (10.1016/j.optlastec.2025.112971_b27) 2023; 92
Li (10.1016/j.optlastec.2025.112971_b8) 2023; 15
Chen (10.1016/j.optlastec.2025.112971_b35) 2021
Xue (10.1016/j.optlastec.2025.112971_b18) 2022; 127
Yang (10.1016/j.optlastec.2025.112971_b9) 2020; 70
Ma (10.1016/j.optlastec.2025.112971_b24) 2019; 48
10.1016/j.optlastec.2025.112971_b52
Peng (10.1016/j.optlastec.2025.112971_b5) 2023; 14
Zhao (10.1016/j.optlastec.2025.112971_b11) 2020
Zhou (10.1016/j.optlastec.2025.112971_b62) 2016; 55
Huang (10.1016/j.optlastec.2025.112971_b14) 2024
Karim (10.1016/j.optlastec.2025.112971_b51) 2023; 90
Ma (10.1016/j.optlastec.2025.112971_b2) 2023; 23
Zuo (10.1016/j.optlastec.2025.112971_b20) 2017; 17
Chang (10.1016/j.optlastec.2025.112971_b1) 2023; 32
Li (10.1016/j.optlastec.2025.112971_b13) 2024; 132
Lin (10.1016/j.optlastec.2025.112971_b40) 2023; 61
Huang (10.1016/j.optlastec.2025.112971_b21) 2018; 18
Wang (10.1016/j.optlastec.2025.112971_b69) 2025; 117
Tang (10.1016/j.optlastec.2025.112971_b46) 2023; 91
Ma (10.1016/j.optlastec.2025.112971_b64) 2017; 82
Gao (10.1016/j.optlastec.2025.112971_b19) 2020; 39
10.1016/j.optlastec.2025.112971_b68
Liu (10.1016/j.optlastec.2025.112971_b28) 2023; 91
Toet (10.1016/j.optlastec.2025.112971_b47) 2017; 15
Xu (10.1016/j.optlastec.2025.112971_b16) 2022; 218
Liu (10.1016/j.optlastec.2025.112971_b33) 2019; 39
Bavirisetti (10.1016/j.optlastec.2025.112971_b63) 2017
Eymaël (10.1016/j.optlastec.2025.112971_b44) 2024
(10.1016/j.optlastec.2025.112971_b58) 2017
Wang (10.1016/j.optlastec.2025.112971_b23) 2021; 32
Tang (10.1016/j.optlastec.2025.112971_b31) 2023; 33
Luo (10.1016/j.optlastec.2025.112971_b50) 2022
Dong (10.1016/j.optlastec.2025.112971_b3) 2023; 12
Wu (10.1016/j.optlastec.2025.112971_b70) 2021; 46
Wang (10.1016/j.optlastec.2025.112971_b26) 2022; 25
Wang (10.1016/j.optlastec.2025.112971_b29) 2023; 72
Ma (10.1016/j.optlastec.2025.112971_b25) 2020; 29
Li (10.1016/j.optlastec.2025.112971_b10) 2018
10.1016/j.optlastec.2025.112971_b36
Liu (10.1016/j.optlastec.2025.112971_b15) 2024; 573
Li (10.1016/j.optlastec.2025.112971_b49) 2023; 17
References_xml – volume: 33
  start-page: 3159
  year: 2023
  end-page: 3172
  ident: b31
  article-title: Datfuse: Infrared and visible image fusion via dual attention transformer
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– start-page: 141
  year: 2020
  end-page: 157
  ident: b38
  article-title: Unsupervised deep metric learning with transformed attention consistency and contrastive clustering loss
  publication-title: European Conference on Computer Vision
– volume: 17
  start-page: 726
  year: 2023
  end-page: 745
  ident: b49
  article-title: Deep CNN denoiser prior for blurred images restoration with multiplicative noise
  publication-title: Inverse Probl. Imaging
– volume: 128
  year: 2023
  ident: b55
  article-title: Infrared and visible image fusion based on residual dense network and gradient loss
  publication-title: Infrared Phys. Technol.
– volume: 88
  start-page: 305
  year: 2022
  end-page: 318
  ident: b66
  article-title: UIFGAN: An unsupervised continual-learning generative adversarial network for unified image fusion
  publication-title: Inf. Fusion
– year: 2017
  ident: b58
  article-title: Flir dataset
– volume: 156
  year: 2024
  ident: b32
  article-title: Itfuse: An interactive transformer for infrared and visible image fusion
  publication-title: Pattern Recognit.
– volume: 15
  start-page: 249
  year: 2017
  end-page: 251
  ident: b47
  article-title: The TNO multiband image data collection
  publication-title: Data Brief
– volume: 31
  year: 2022
  ident: b17
  article-title: Mefuse: end-to-end infrared and visible image fusion method based on multibranch encoder
  publication-title: J. Electron. Imaging
– year: 2023
  ident: b34
  article-title: Llm-blender: Ensembling large language models with pairwise ranking and generative fusion
– reference: Xinyu Jia, Chuang Zhu, Minzhen Li, Wenqi Tang, Wenli Zhou, LLVIP: A visible-infrared paired dataset for low-light vision, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 3496–3504.
– volume: 14
  start-page: 2789
  year: 2022
  ident: b4
  article-title: Infrared and visible image fusion with deep neural network in enhanced flight vision system
  publication-title: Remote. Sens.
– volume: 83
  start-page: 79
  year: 2022
  end-page: 92
  ident: b60
  article-title: Piafusion: A progressive infrared and visible image fusion network based on illumination aware
  publication-title: Inf. Fusion
– volume: 573
  year: 2024
  ident: b15
  article-title: WaveFusionNet: Infrared and visible image fusion based on multi-scale feature encoder–decoder and discrete wavelet decomposition
  publication-title: Opt. Commun.
– volume: 70
  start-page: 1
  year: 2020
  end-page: 15
  ident: b9
  article-title: Infrared and visible image fusion using visual saliency sparse representation and detail injection model
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 61
  start-page: 1
  year: 2023
  end-page: 12
  ident: b12
  article-title: LRR-Net: An interpretable deep unfolding network for hyperspectral anomaly detection
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 39
  start-page: 4617
  year: 2020
  end-page: 4629
  ident: b19
  article-title: Infrared and visible image fusion using dual-tree complex wavelet transform and convolutional sparse representation
  publication-title: J. Intell. Fuzzy Systems
– volume: 25
  start-page: 7800
  year: 2022
  end-page: 7813
  ident: b26
  article-title: Infrared and visible image fusion via interactive compensatory attention adversarial learning
  publication-title: IEEE Trans. Multimed.
– start-page: 2705
  year: 2018
  end-page: 2710
  ident: b10
  article-title: Infrared and visible image fusion using a deep learning framework
  publication-title: 2018 24th International Conference on Pattern Recognition
– volume: 91
  start-page: 477
  year: 2023
  end-page: 493
  ident: b46
  article-title: Divfusion: Darkness-free infrared and visible image fusion
  publication-title: Inf. Fusion
– volume: 73
  start-page: 72
  year: 2021
  end-page: 86
  ident: b22
  article-title: RFN-Nest: An end-to-end residual fusion network for infrared and visible images
  publication-title: Inf. Fusion
– volume: 218
  year: 2022
  ident: b16
  article-title: CUFD: An encoder–decoder network for visible and infrared image fusion based on common and unique feature decomposition
  publication-title: Comput. Vis. Image Underst.
– year: 2024
  ident: b41
  article-title: Audio super-resolution with robust speech representation learning of masked autoencoder
  publication-title: IEEE/ACM Trans. Audio Speech Lang. Process.
– volume: 9
  start-page: 1103
  year: 2019
  ident: b48
  article-title: Learning deep CNN denoiser priors for depth image inpainting
  publication-title: Appl. Sci.
– volume: 29
  start-page: 4980
  year: 2020
  end-page: 4995
  ident: b25
  article-title: DDcGAN: A dual-discriminator conditional generative adversarial network for multi-resolution image fusion
  publication-title: IEEE Trans. Image Process.
– year: 2022
  ident: b50
  article-title: Learning the degradation distribution for blind image super-resolution
– volume: 91
  start-page: 205
  year: 2023
  end-page: 214
  ident: b28
  article-title: Sgfusion: A saliency guided deep-learning framework for pixel-level image fusion
  publication-title: Inf. Fusion
– volume: 54
  start-page: 99
  year: 2020
  end-page: 118
  ident: b67
  article-title: IFCNN: A general image fusion framework based on convolutional neural network
  publication-title: Inf. Fusion
– reference: Yiming Sun, Bing Cao, Pengfei Zhu, Qinghua Hu, Detfusion: A detection-driven infrared and visible image fusion network, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 4003–4011.
– volume: 55
  start-page: 6480
  year: 2016
  end-page: 6490
  ident: b62
  article-title: Fusion of infrared and visible images for night-vision context enhancement
  publication-title: Appl. Opt.
– volume: 18
  start-page: 1169
  year: 2018
  ident: b21
  article-title: Infrared and visible image fusion based on different constraints in the non-subsampled shearlet transform domain
  publication-title: Sensors
– volume: 48
  start-page: 11
  year: 2019
  end-page: 26
  ident: b24
  article-title: FusionGAN: A generative adversarial network for infrared and visible image fusion
  publication-title: Inf. Fusion
– volume: 12
  start-page: 1732
  year: 2023
  ident: b3
  article-title: Research on detection and recognition technology of a visible and infrared dim and small target based on deep learning
  publication-title: Electron.
– reference: Ze Liu, Jia Ning, Yue Cao, Yixuan Wei, Zheng Zhang, Stephen Lin, Han Hu, Video swin transformer, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 3202–3211.
– volume: 45
  start-page: 7220
  year: 2022
  end-page: 7238
  ident: b39
  article-title: Contrastive bayesian analysis for deep metric learning
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 90
  start-page: 185
  year: 2023
  end-page: 217
  ident: b51
  article-title: Current advances and future perspectives of image fusion: A comprehensive review
  publication-title: Inf. Fusion
– volume: 54
  start-page: 85
  year: 2020
  end-page: 98
  ident: b57
  article-title: Infrared and visible image fusion via detail preserving adversarial learning
  publication-title: Inf. Fusion
– volume: 132
  start-page: 1625
  year: 2024
  end-page: 1644
  ident: b13
  article-title: A deep learning framework for infrared and visible image fusion without strict registration
  publication-title: Int. J. Comput. Vis.
– year: 2024
  ident: b14
  article-title: Spatiotemporal enhancement and interlevel fusion network for remote sensing images change detection
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 204
  year: 2023
  ident: b53
  article-title: Modified U-Net for plant diseased leaf image segmentation
  publication-title: Comput. Electron. Agric.
– volume: 39
  start-page: 718
  year: 2019
  end-page: 728
  ident: b33
  article-title: Multi-task deep model with margin ranking loss for lung nodule analysis
  publication-title: IEEE Trans. Med. Imaging
– volume: 61
  start-page: 1
  year: 2023
  end-page: 14
  ident: b40
  article-title: SS-MAE: Spatial–spectral masked autoencoder for multisource remote sensing image classification
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 249
  year: 2024
  ident: b45
  article-title: Mfhod: Multi-modal image fusion method based on the higher-order degradation model
  publication-title: Expert Syst. Appl.
– volume: 17
  start-page: 1127
  year: 2017
  ident: b20
  article-title: Airborne infrared and visible image fusion combined with region segmentation
  publication-title: Sensors
– volume: 80
  start-page: 8423
  year: 2021
  end-page: 8444
  ident: b56
  article-title: PSNR vs SSIM: imperceptibility quality assessment for image steganography
  publication-title: Multimedia Tools Appl.
– volume: 46
  start-page: 2908
  year: 2021
  end-page: 2911
  ident: b70
  article-title: High-speed computer-generated holography using an autoencoder-based deep neural network
  publication-title: Opt. Lett.
– volume: 29
  start-page: 457
  year: 2023
  end-page: 467
  ident: b7
  article-title: IR and visible image fusion using DWT and bilateral filter
  publication-title: Microsyst. Technol.
– volume: 32
  start-page: 3360
  year: 2021
  end-page: 3374
  ident: b23
  article-title: Unfusion: A unified multi-scale densely connected network for infrared and visible image fusion
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– volume: 92
  start-page: 80
  year: 2023
  end-page: 92
  ident: b27
  article-title: Mufusion: A general unsupervised image fusion network based on memory unit
  publication-title: Inf. Fusion
– volume: 83
  start-page: 227
  year: 2017
  end-page: 237
  ident: b65
  article-title: Infrared and visual image fusion through infrared feature extraction and visual information preservation
  publication-title: Infrared Phys. Technol.
– start-page: 1
  year: 2017
  end-page: 9
  ident: b63
  article-title: Multi-sensor image fusion based on fourth order partial differential equations
  publication-title: 2017 20th International Conference on Information Fusion (Fusion)
– volume: 127
  year: 2022
  ident: b18
  article-title: Flfuse-net: A fast and lightweight infrared and visible image fusion network via feature flow and edge compensation for salient information
  publication-title: Infrared Phys. Technol.
– volume: 25
  start-page: 5413
  year: 2022
  end-page: 5428
  ident: b30
  article-title: YDTR: Infrared and visible image fusion via Y-shape dynamic transformer
  publication-title: IEEE Trans. Multimed.
– year: 2021
  ident: b35
  article-title: Poolrank: Max/min pooling-based ranking loss for listwise learning & ranking balance
– start-page: 127
  year: 2020
  end-page: 144
  ident: b6
  article-title: A review on infrared and visible image fusion techniques
  publication-title: Intelligent Communication Technologies and Virtual Mobile Networks: ICICV 2019
– volume: 117
  year: 2025
  ident: b69
  article-title: SMAE-fusion: Integrating saliency-aware masked autoencoder with hybrid attention transformer for infrared–visible image fusion
  publication-title: Inf. Fusion
– year: 2020
  ident: b11
  article-title: DIDFuse: Deep image decomposition for infrared and visible image fusion
– volume: 80
  year: 2023
  ident: b37
  article-title: Deep metric learning with mirror attention and fine triplet loss for fundus image retrieval in ophthalmology
  publication-title: Biomed. Signal Process. Control.
– year: 2024
  ident: b44
  article-title: Efficient image pre-training with siamese cropped masked autoencoders
– volume: 23
  start-page: 599
  year: 2023
  ident: b2
  article-title: Infrared and visible image fusion technology and application: A review
  publication-title: Sensors
– volume: 14
  start-page: 3281
  year: 2023
  end-page: 3293
  ident: b5
  article-title: Siamese infrared and visible light fusion network for RGB-T tracking
  publication-title: Int. J. Mach. Learn. Cybern.
– reference: Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick, Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16000–16009.
– volume: 32
  start-page: 2077
  year: 2023
  end-page: 2092
  ident: b1
  article-title: AFT: Adaptive fusion transformer for visible and infrared images
  publication-title: IEEE Trans. Image Process.
– volume: 15
  start-page: 685
  year: 2023
  ident: b8
  article-title: Infrared and visible image fusion method based on a principal component analysis network and image pyramid
  publication-title: Remote. Sens.
– volume: 72
  start-page: 1
  year: 2023
  end-page: 12
  ident: b29
  article-title: Fusiongram: An infrared and visible image fusion framework based on gradient residual and attention mechanism
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 36
  start-page: 40676
  year: 2023
  end-page: 40693
  ident: b43
  article-title: Siamese masked autoencoders
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 30
  start-page: 15
  year: 2016
  end-page: 26
  ident: b61
  article-title: Perceptual fusion of infrared and visible images through a hybrid multi-scale decomposition with Gaussian and bilateral filters
  publication-title: Inf. Fusion
– reference: Weifeng Ge, Deep metric learning with hierarchical triplet loss, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 269–285.
– reference: Jiawei Ren, Mingyuan Zhang, Cunjun Yu, Ziwei Liu, Balanced mse for imbalanced visual regression, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7926–7935.
– volume: 82
  start-page: 8
  year: 2017
  end-page: 17
  ident: b64
  article-title: Infrared and visible image fusion based on visual saliency map and weighted least square optimization
  publication-title: Infrared Phys. Technol.
– volume: 132
  start-page: 1625
  issue: 5
  year: 2024
  ident: 10.1016/j.optlastec.2025.112971_b13
  article-title: A deep learning framework for infrared and visible image fusion without strict registration
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-023-01948-x
– volume: 14
  start-page: 3281
  issue: 9
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b5
  article-title: Siamese infrared and visible light fusion network for RGB-T tracking
  publication-title: Int. J. Mach. Learn. Cybern.
  doi: 10.1007/s13042-023-01833-6
– volume: 91
  start-page: 205
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b28
  article-title: Sgfusion: A saliency guided deep-learning framework for pixel-level image fusion
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2022.09.030
– volume: 83
  start-page: 79
  year: 2022
  ident: 10.1016/j.optlastec.2025.112971_b60
  article-title: Piafusion: A progressive infrared and visible image fusion network based on illumination aware
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2022.03.007
– ident: 10.1016/j.optlastec.2025.112971_b59
  doi: 10.1109/ICCVW54120.2021.00389
– volume: 573
  year: 2024
  ident: 10.1016/j.optlastec.2025.112971_b15
  article-title: WaveFusionNet: Infrared and visible image fusion based on multi-scale feature encoder–decoder and discrete wavelet decomposition
  publication-title: Opt. Commun.
  doi: 10.1016/j.optcom.2024.131024
– volume: 9
  start-page: 1103
  issue: 6
  year: 2019
  ident: 10.1016/j.optlastec.2025.112971_b48
  article-title: Learning deep CNN denoiser priors for depth image inpainting
  publication-title: Appl. Sci.
  doi: 10.3390/app9061103
– year: 2024
  ident: 10.1016/j.optlastec.2025.112971_b14
  article-title: Spatiotemporal enhancement and interlevel fusion network for remote sensing images change detection
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 25
  start-page: 7800
  year: 2022
  ident: 10.1016/j.optlastec.2025.112971_b26
  article-title: Infrared and visible image fusion via interactive compensatory attention adversarial learning
  publication-title: IEEE Trans. Multimed.
  doi: 10.1109/TMM.2022.3228685
– ident: 10.1016/j.optlastec.2025.112971_b42
– year: 2021
  ident: 10.1016/j.optlastec.2025.112971_b35
– year: 2024
  ident: 10.1016/j.optlastec.2025.112971_b44
– volume: 88
  start-page: 305
  year: 2022
  ident: 10.1016/j.optlastec.2025.112971_b66
  article-title: UIFGAN: An unsupervised continual-learning generative adversarial network for unified image fusion
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2022.07.013
– volume: 70
  start-page: 1
  year: 2020
  ident: 10.1016/j.optlastec.2025.112971_b9
  article-title: Infrared and visible image fusion using visual saliency sparse representation and detail injection model
  publication-title: IEEE Trans. Instrum. Meas.
  doi: 10.1109/TIM.2020.2986875
– volume: 82
  start-page: 8
  year: 2017
  ident: 10.1016/j.optlastec.2025.112971_b64
  article-title: Infrared and visible image fusion based on visual saliency map and weighted least square optimization
  publication-title: Infrared Phys. Technol.
  doi: 10.1016/j.infrared.2017.02.005
– volume: 15
  start-page: 249
  year: 2017
  ident: 10.1016/j.optlastec.2025.112971_b47
  article-title: The TNO multiband image data collection
  publication-title: Data Brief
  doi: 10.1016/j.dib.2017.09.038
– volume: 73
  start-page: 72
  year: 2021
  ident: 10.1016/j.optlastec.2025.112971_b22
  article-title: RFN-Nest: An end-to-end residual fusion network for infrared and visible images
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2021.02.023
– volume: 90
  start-page: 185
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b51
  article-title: Current advances and future perspectives of image fusion: A comprehensive review
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2022.09.019
– volume: 127
  year: 2022
  ident: 10.1016/j.optlastec.2025.112971_b18
  article-title: Flfuse-net: A fast and lightweight infrared and visible image fusion network via feature flow and edge compensation for salient information
  publication-title: Infrared Phys. Technol.
  doi: 10.1016/j.infrared.2022.104383
– volume: 45
  start-page: 7220
  issue: 6
  year: 2022
  ident: 10.1016/j.optlastec.2025.112971_b39
  article-title: Contrastive bayesian analysis for deep metric learning
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2022.3221486
– volume: 117
  year: 2025
  ident: 10.1016/j.optlastec.2025.112971_b69
  article-title: SMAE-fusion: Integrating saliency-aware masked autoencoder with hybrid attention transformer for infrared–visible image fusion
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2024.102841
– start-page: 127
  year: 2020
  ident: 10.1016/j.optlastec.2025.112971_b6
  article-title: A review on infrared and visible image fusion techniques
– volume: 31
  issue: 3
  year: 2022
  ident: 10.1016/j.optlastec.2025.112971_b17
  article-title: Mefuse: end-to-end infrared and visible image fusion method based on multibranch encoder
  publication-title: J. Electron. Imaging
  doi: 10.1117/1.JEI.31.3.033043
– volume: 39
  start-page: 4617
  issue: 3
  year: 2020
  ident: 10.1016/j.optlastec.2025.112971_b19
  article-title: Infrared and visible image fusion using dual-tree complex wavelet transform and convolutional sparse representation
  publication-title: J. Intell. Fuzzy Systems
– volume: 54
  start-page: 85
  year: 2020
  ident: 10.1016/j.optlastec.2025.112971_b57
  article-title: Infrared and visible image fusion via detail preserving adversarial learning
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2019.07.005
– volume: 18
  start-page: 1169
  issue: 4
  year: 2018
  ident: 10.1016/j.optlastec.2025.112971_b21
  article-title: Infrared and visible image fusion based on different constraints in the non-subsampled shearlet transform domain
  publication-title: Sensors
  doi: 10.3390/s18041169
– volume: 92
  start-page: 80
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b27
  article-title: Mufusion: A general unsupervised image fusion network based on memory unit
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2022.11.010
– volume: 39
  start-page: 718
  issue: 3
  year: 2019
  ident: 10.1016/j.optlastec.2025.112971_b33
  article-title: Multi-task deep model with margin ranking loss for lung nodule analysis
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/TMI.2019.2934577
– volume: 249
  year: 2024
  ident: 10.1016/j.optlastec.2025.112971_b45
  article-title: Mfhod: Multi-modal image fusion method based on the higher-order degradation model
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2024.123731
– volume: 17
  start-page: 726
  issue: 3
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b49
  article-title: Deep CNN denoiser prior for blurred images restoration with multiplicative noise
  publication-title: Inverse Probl. Imaging
  doi: 10.3934/ipi.2022075
– year: 2024
  ident: 10.1016/j.optlastec.2025.112971_b41
  article-title: Audio super-resolution with robust speech representation learning of masked autoencoder
  publication-title: IEEE/ACM Trans. Audio Speech Lang. Process.
  doi: 10.1109/TASLP.2023.3349053
– volume: 25
  start-page: 5413
  year: 2022
  ident: 10.1016/j.optlastec.2025.112971_b30
  article-title: YDTR: Infrared and visible image fusion via Y-shape dynamic transformer
  publication-title: IEEE Trans. Multimed.
  doi: 10.1109/TMM.2022.3192661
– volume: 54
  start-page: 99
  year: 2020
  ident: 10.1016/j.optlastec.2025.112971_b67
  article-title: IFCNN: A general image fusion framework based on convolutional neural network
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2019.07.011
– ident: 10.1016/j.optlastec.2025.112971_b36
– volume: 72
  start-page: 1
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b29
  article-title: Fusiongram: An infrared and visible image fusion framework based on gradient residual and attention mechanism
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 55
  start-page: 6480
  issue: 23
  year: 2016
  ident: 10.1016/j.optlastec.2025.112971_b62
  article-title: Fusion of infrared and visible images for night-vision context enhancement
  publication-title: Appl. Opt.
  doi: 10.1364/AO.55.006480
– start-page: 2705
  year: 2018
  ident: 10.1016/j.optlastec.2025.112971_b10
  article-title: Infrared and visible image fusion using a deep learning framework
– volume: 17
  start-page: 1127
  issue: 5
  year: 2017
  ident: 10.1016/j.optlastec.2025.112971_b20
  article-title: Airborne infrared and visible image fusion combined with region segmentation
  publication-title: Sensors
  doi: 10.3390/s17051127
– volume: 33
  start-page: 3159
  issue: 7
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b31
  article-title: Datfuse: Infrared and visible image fusion via dual attention transformer
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2023.3234340
– start-page: 141
  year: 2020
  ident: 10.1016/j.optlastec.2025.112971_b38
  article-title: Unsupervised deep metric learning with transformed attention consistency and contrastive clustering loss
– volume: 32
  start-page: 3360
  issue: 6
  year: 2021
  ident: 10.1016/j.optlastec.2025.112971_b23
  article-title: Unfusion: A unified multi-scale densely connected network for infrared and visible image fusion
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2021.3109895
– volume: 80
  start-page: 8423
  issue: 6
  year: 2021
  ident: 10.1016/j.optlastec.2025.112971_b56
  article-title: PSNR vs SSIM: imperceptibility quality assessment for image steganography
  publication-title: Multimedia Tools Appl.
  doi: 10.1007/s11042-020-10035-z
– volume: 29
  start-page: 457
  issue: 4
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b7
  article-title: IR and visible image fusion using DWT and bilateral filter
  publication-title: Microsyst. Technol.
  doi: 10.1007/s00542-022-05315-7
– ident: 10.1016/j.optlastec.2025.112971_b68
  doi: 10.1145/3503161.3547902
– year: 2020
  ident: 10.1016/j.optlastec.2025.112971_b11
– ident: 10.1016/j.optlastec.2025.112971_b52
  doi: 10.1109/CVPR52688.2022.00320
– volume: 46
  start-page: 2908
  issue: 12
  year: 2021
  ident: 10.1016/j.optlastec.2025.112971_b70
  article-title: High-speed computer-generated holography using an autoencoder-based deep neural network
  publication-title: Opt. Lett.
  doi: 10.1364/OL.425485
– volume: 156
  year: 2024
  ident: 10.1016/j.optlastec.2025.112971_b32
  article-title: Itfuse: An interactive transformer for infrared and visible image fusion
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2024.110822
– volume: 12
  start-page: 1732
  issue: 7
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b3
  article-title: Research on detection and recognition technology of a visible and infrared dim and small target based on deep learning
  publication-title: Electron.
  doi: 10.3390/electronics12071732
– volume: 30
  start-page: 15
  year: 2016
  ident: 10.1016/j.optlastec.2025.112971_b61
  article-title: Perceptual fusion of infrared and visible images through a hybrid multi-scale decomposition with Gaussian and bilateral filters
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2015.11.003
– volume: 48
  start-page: 11
  year: 2019
  ident: 10.1016/j.optlastec.2025.112971_b24
  article-title: FusionGAN: A generative adversarial network for infrared and visible image fusion
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2018.09.004
– volume: 128
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b55
  article-title: Infrared and visible image fusion based on residual dense network and gradient loss
  publication-title: Infrared Phys. Technol.
  doi: 10.1016/j.infrared.2022.104486
– volume: 14
  start-page: 2789
  issue: 12
  year: 2022
  ident: 10.1016/j.optlastec.2025.112971_b4
  article-title: Infrared and visible image fusion with deep neural network in enhanced flight vision system
  publication-title: Remote. Sens.
  doi: 10.3390/rs14122789
– volume: 83
  start-page: 227
  year: 2017
  ident: 10.1016/j.optlastec.2025.112971_b65
  article-title: Infrared and visual image fusion through infrared feature extraction and visual information preservation
  publication-title: Infrared Phys. Technol.
  doi: 10.1016/j.infrared.2017.05.007
– year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b34
– ident: 10.1016/j.optlastec.2025.112971_b54
– volume: 36
  start-page: 40676
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b43
  article-title: Siamese masked autoencoders
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 61
  start-page: 1
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b40
  article-title: SS-MAE: Spatial–spectral masked autoencoder for multisource remote sensing image classification
  publication-title: IEEE Trans. Geosci. Remote Sens.
  doi: 10.1109/TGRS.2023.3334729
– volume: 15
  start-page: 685
  issue: 3
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b8
  article-title: Infrared and visible image fusion method based on a principal component analysis network and image pyramid
  publication-title: Remote. Sens.
  doi: 10.3390/rs15030685
– volume: 218
  year: 2022
  ident: 10.1016/j.optlastec.2025.112971_b16
  article-title: CUFD: An encoder–decoder network for visible and infrared image fusion based on common and unique feature decomposition
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2022.103407
– volume: 91
  start-page: 477
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b46
  article-title: Divfusion: Darkness-free infrared and visible image fusion
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2022.10.034
– volume: 80
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b37
  article-title: Deep metric learning with mirror attention and fine triplet loss for fundus image retrieval in ophthalmology
  publication-title: Biomed. Signal Process. Control.
  doi: 10.1016/j.bspc.2022.104277
– year: 2017
  ident: 10.1016/j.optlastec.2025.112971_b58
– start-page: 1
  year: 2017
  ident: 10.1016/j.optlastec.2025.112971_b63
  article-title: Multi-sensor image fusion based on fourth order partial differential equations
– year: 2022
  ident: 10.1016/j.optlastec.2025.112971_b50
– volume: 29
  start-page: 4980
  year: 2020
  ident: 10.1016/j.optlastec.2025.112971_b25
  article-title: DDcGAN: A dual-discriminator conditional generative adversarial network for multi-resolution image fusion
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2020.2977573
– volume: 23
  start-page: 599
  issue: 2
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b2
  article-title: Infrared and visible image fusion technology and application: A review
  publication-title: Sensors
  doi: 10.3390/s23020599
– volume: 32
  start-page: 2077
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b1
  article-title: AFT: Adaptive fusion transformer for visible and infrared images
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2023.3263113
– volume: 61
  start-page: 1
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b12
  article-title: LRR-Net: An interpretable deep unfolding network for hyperspectral anomaly detection
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 204
  year: 2023
  ident: 10.1016/j.optlastec.2025.112971_b53
  article-title: Modified U-Net for plant diseased leaf image segmentation
  publication-title: Comput. Electron. Agric.
  doi: 10.1016/j.compag.2022.107511
SSID ssj0004653
Score 2.418553
Snippet The task of infrared and visible image fusion aims to retain the thermal targets from infrared images while preserving the details, brightness, and other...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 112971
SubjectTerms Deep learning
Image degradation
Image fusion
Masked autoencoder
Metric space
Title MRFuse: Metric learning and masked autoencoder for fusing real infrared and visible images
URI https://dx.doi.org/10.1016/j.optlastec.2025.112971
Volume 189
WOSCitedRecordID wos001508785100001&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
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 0030-3992
  databaseCode: AIEXJ
  dateStart: 19950201
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0004653
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELagBakcKihUFArygWuqPJzE7q2gPkC0ICjSwiWyY1tKUbPRJqn25zN-JBvKSoAQl2gVOc5m5tNkdna-bxB6JTiRpKQioCrJAhKFOoCXAglImoeMUqE5Le2wifzigs5m7KOnELR2nEBe13S5ZM1_dTWcA2cb6uxfuHvcFE7AZ3A6HMHtcPwjx59_Oukd4_zcTMsqh8EQjot4zdvvkGPyvpsbCUujJGEaDXVvawYLZTU49MK2pZv1hntuyFXVNQSedprKfmhGhWfIwGGf7pcq_XvbKvC1f12NEDQFatvXp6pVLeC0d___VPVyurJ3AbFR_u3qixNx6ll6Y8VsYM2sWpRsFE4g9jN2KwqztRHdFReuDuZNBw8DT3Jg7mOYT8zNbrkll_3Z7G7VdlMjcxpnd9FmnKcMgvbm0dvj2bsJa9ZrlPpv81P339rbrc9dJvnI5UO07X9I4CMHgEfojqp30IOJvOQOum_be8v2MfrmQHGIHSTwAAkM3sMOEngCCQyQwA4S2EACD5Cw6z0ksIPEE_Tl5PjyzVngp2oEZZwlXSBEEsmIG1miLNRCaZVoRnVpJhvkEeEkjHkWSalZQnOeiExllOdZKUtJpIbsbxdt1PNaPUWYUQ7ZJRGMK0EET5kMtY5yJbXKIDMP91A42KtonHhKMXQVXhWjiQtj4sKZeA8dDnYtfA7ocrsCAPG7i5_9y8XP0dYKwftoo1v06gW6V950Vbt46cHzAzHVh5M
linkProvider Elsevier
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=MRFuse%3A+Metric+learning+and+masked+autoencoder+for+fusing+real+infrared+and+visible+images&rft.jtitle=Optics+and+laser+technology&rft.au=Li%2C+YuBin&rft.au=Zhan%2C+Weida&rft.au=Guo%2C+Jinxin&rft.au=Zhu%2C+Depeng&rft.date=2025-11-01&rft.pub=Elsevier+Ltd&rft.issn=0030-3992&rft.volume=189&rft_id=info:doi/10.1016%2Fj.optlastec.2025.112971&rft.externalDocID=S0030399225005626
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0030-3992&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0030-3992&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0030-3992&client=summon