EBStereo: edge-based loss function for real-time stereo matching

Deep learning-based stereo matching has made significant progress, but it still faces challenges: The disparity prediction error maps of current models show that errors are concentrated primarily on object boundaries. We find that executing the smooth L1 loss function on the entire region during ste...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Visual computer Jg. 40; H. 4; S. 2975 - 2986
Hauptverfasser: Bi, Weijie, Chen, Ming, Wu, Dongliu, Lu, Shenglian
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2024
Springer Nature B.V
Schlagworte:
ISSN:0178-2789, 1432-2315
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Deep learning-based stereo matching has made significant progress, but it still faces challenges: The disparity prediction error maps of current models show that errors are concentrated primarily on object boundaries. We find that executing the smooth L1 loss function on the entire region during stereo matching model training cannot effectively address the imbalance between edge regions and flat regions, resulting in poor disparity estimates for edge regions. In this paper, a new weighted smooth L1 loss function, which considers the loss function calculation on edge regions and can yield improved accuracy, is proposed. An improved bilateral grid upsampling module is also added to the training model, and a strategy is adopted to balance the computational consumption introduced by the new loss function-weighted item, allowing for real-time inference. Extensive experiments conducted on two datasets, i.e., Scene Flow and KITTI, verify the simplicity and effectiveness of this approach. Under the condition of 33 frames per second (FPS), the endpoint error of the proposed model can be improved to 0.63. In addition, the proposed edge-based loss function can be easily embedded into many existing stereo matching networks, such as GwcNet, AANet, and PSMNet. After embedding the proposed edge-based loss function, the reduction rates of the endpoint errors of the existing models can be improved to 3.5%, 11.6%, and 27.2% for GwcNet, AANet, and PSMNet, respectively.
AbstractList Deep learning-based stereo matching has made significant progress, but it still faces challenges: The disparity prediction error maps of current models show that errors are concentrated primarily on object boundaries. We find that executing the smooth L1 loss function on the entire region during stereo matching model training cannot effectively address the imbalance between edge regions and flat regions, resulting in poor disparity estimates for edge regions. In this paper, a new weighted smooth L1 loss function, which considers the loss function calculation on edge regions and can yield improved accuracy, is proposed. An improved bilateral grid upsampling module is also added to the training model, and a strategy is adopted to balance the computational consumption introduced by the new loss function-weighted item, allowing for real-time inference. Extensive experiments conducted on two datasets, i.e., Scene Flow and KITTI, verify the simplicity and effectiveness of this approach. Under the condition of 33 frames per second (FPS), the endpoint error of the proposed model can be improved to 0.63. In addition, the proposed edge-based loss function can be easily embedded into many existing stereo matching networks, such as GwcNet, AANet, and PSMNet. After embedding the proposed edge-based loss function, the reduction rates of the endpoint errors of the existing models can be improved to 3.5%, 11.6%, and 27.2% for GwcNet, AANet, and PSMNet, respectively.
Author Wu, Dongliu
Lu, Shenglian
Chen, Ming
Bi, Weijie
Author_xml – sequence: 1
  givenname: Weijie
  surname: Bi
  fullname: Bi, Weijie
  organization: School of Computer Science and Engineering, Guangxi Normal University
– sequence: 2
  givenname: Ming
  surname: Chen
  fullname: Chen, Ming
  email: hustcm@hotmail.com
  organization: School of Computer Science and Engineering, Guangxi Normal University, Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University
– sequence: 3
  givenname: Dongliu
  surname: Wu
  fullname: Wu, Dongliu
  organization: School of Computer Science and Engineering, Guangxi Normal University
– sequence: 4
  givenname: Shenglian
  surname: Lu
  fullname: Lu, Shenglian
  organization: School of Computer Science and Engineering, Guangxi Normal University, Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University
BookMark eNqFkE1LAzEQhoNUsK3-AU8LnqOTzG6T9aSW-gEFD-o5ZDeTuqXdrcmW4r932xUED3oaBp5nPt4RG9RNTYydC7gUAOoqAqASHCRyQADJd0dsKFKUXKLIBmwIQmkulc5P2CjGJXS9SvMhu5ndvbQUqLlOyC2IFzaSS1ZNjInf1mVbNXXim5AEsiveVmtK4gFP1rYt36t6ccqOvV1FOvuuY_Z2P3udPvL588PT9HbOS0xVy7WTuVMyz3xqXeqkRPKqnBReOQBLKZJEL8oCC0kySwuBQjhQmcKJdBoljtlFP3cTmo8txdYsm22ou5UGAVFr0CL7j1JS5FneUbqnytA9Gsibsmrt_tc22GplBJh9qqZP1XSpmkOqZtep8pe6CdXahs-_Jeyl2MH1gsLPVX9YX3Ygils
CitedBy_id crossref_primary_10_3390_electronics13112024
crossref_primary_10_1364_AO_564771
Cites_doi 10.1109/TCSVT.2009.2020478
10.1145/3072959.3073592
10.1007/s11432-019-2803-x
10.1109/TPAMI.2007.1043
10.1145/2980179.2982423
10.1145/1276377.1276506
10.1109/TPAMI.1986.4767851
10.1023/A:1014573219977
10.1109/TPAMI.2007.1166
10.1007/s00371-021-02228-w
10.1007/s00371-018-1491-0
10.1007/s00034-009-9130-7
10.1016/j.eswa.2022.118573
10.1109/TPAMI.2003.1206509
10.1109/LSP.2021.3066125
10.1016/j.engstruct.2022.115158
10.1109/LRA.2022.3143895
10.1016/j.compag.2021.106107
10.1109/CVPR.2019.00339
10.1109/ICCV.2019.00448
10.1109/ICCV.2015.316
10.1109/CVPR.2018.00920
10.1109/CVPR52688.2022.01264
10.1109/CVPR42600.2020.00203
10.1109/CVPR46437.2021.01592
10.5194/isprsannals-II-3-W5-427-2015
10.1109/CVPR46437.2021.00539
10.1109/CVPR.2019.00027
10.1109/WACV51458.2022.00075
10.1007/978-3-319-11752-2_3
10.1007/978-3-030-01234-2_39
10.1109/ICCV.2017.324
10.1109/ICCV48922.2021.00441
10.1109/CRV.2014.56
10.1007/11744085_44
10.1109/CVPR.2016.438
10.1609/aaai.v36i2.20056
10.1109/CVPR.2018.00567
10.1109/IVS.2013.6629487
10.1109/ICCVW.2017.108
10.1109/CVPR.2012.6248074
10.1007/978-3-030-20873-8_2
10.1109/CVPR.2015.7298767
10.1109/ICCV.2017.17
10.1007/978-3-030-01267-0_35
10.1109/ICRA40945.2020.9197031
10.1609/aaai.v34i07.6991
10.1109/CVPRW.2010.5543769
10.1109/ICASSP.2018.8461664
10.1109/ICCV.2001.937668
10.1109/CVPR.2016.90
ContentType Journal Article
Copyright The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Copyright_xml – notice: The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
DBID AAYXX
CITATION
8FE
8FG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
GNUQQ
HCIFZ
JQ2
K7-
P5Z
P62
PHGZM
PHGZT
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
DOI 10.1007/s00371-023-03002-w
DatabaseName CrossRef
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central UK/Ireland
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Central
Technology Collection
ProQuest One Community College
ProQuest Central
ProQuest Central Student
SciTech Premium
ProQuest Computer Science Collection
Computer Science Database
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic (New)
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
DatabaseTitle CrossRef
Advanced Technologies & Aerospace Collection
Computer Science Database
ProQuest Central Student
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
ProQuest One Academic Eastern Edition
SciTech Premium Collection
ProQuest One Community College
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Central China
ProQuest Central
Advanced Technologies & Aerospace Database
ProQuest One Applied & Life Sciences
ProQuest One Academic UKI Edition
ProQuest Central Korea
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList Advanced Technologies & Aerospace Collection
ProQuest Computer Science Collection

Database_xml – sequence: 1
  dbid: P5Z
  name: Advanced Technologies & Aerospace Database
  url: https://search.proquest.com/hightechjournals
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1432-2315
EndPage 2986
ExternalDocumentID 10_1007_s00371_023_03002_w
GrantInformation_xml – fundername: Natural Science Foundation of Jilin Province
  grantid: 62062015
  funderid: http://dx.doi.org/10.13039/100007847
GroupedDBID -4Z
-59
-5G
-BR
-EM
-Y2
-~C
-~X
.86
.DC
.VR
06D
0R~
0VY
123
1N0
1SB
2.D
203
28-
29R
2J2
2JN
2JY
2KG
2KM
2LR
2P1
2VQ
2~H
30V
4.4
406
408
409
40D
40E
5QI
5VS
67Z
6NX
6TJ
78A
8TC
8UJ
95-
95.
95~
96X
AAAVM
AABHQ
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AAOBN
AARHV
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYOK
AAYQN
AAYTO
AAYZH
ABAKF
ABBBX
ABBXA
ABDPE
ABDZT
ABECU
ABFTV
ABHLI
ABHQN
ABJNI
ABJOX
ABKCH
ABKTR
ABMNI
ABMQK
ABNWP
ABQBU
ABQSL
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABULA
ABWNU
ABXPI
ACAOD
ACBXY
ACDTI
ACGFS
ACHSB
ACHXU
ACKNC
ACMDZ
ACMLO
ACOKC
ACOMO
ACPIV
ACZOJ
ADHHG
ADHIR
ADIMF
ADINQ
ADKNI
ADKPE
ADQRH
ADRFC
ADTPH
ADURQ
ADYFF
ADZKW
AEBTG
AEFIE
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEKMD
AEMSY
AENEX
AEOHA
AEPYU
AESKC
AETLH
AEVLU
AEXYK
AFBBN
AFEXP
AFFNX
AFGCZ
AFKRA
AFLOW
AFQWF
AFWTZ
AFZKB
AGAYW
AGDGC
AGGDS
AGJBK
AGMZJ
AGQEE
AGQMX
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHSBF
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AJBLW
AJRNO
AJZVZ
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMXSW
AMYLF
AMYQR
AOCGG
ARAPS
ARMRJ
ASPBG
AVWKF
AXYYD
AYJHY
AZFZN
B-.
BA0
BBWZM
BDATZ
BENPR
BGLVJ
BGNMA
BSONS
CAG
CCPQU
COF
CS3
CSCUP
DDRTE
DL5
DNIVK
DPUIP
DU5
EBLON
EBS
EIOEI
EJD
ESBYG
FEDTE
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRRFC
FSGXE
FWDCC
GGCAI
GGRSB
GJIRD
GNWQR
GQ6
GQ7
GQ8
GXS
H13
HCIFZ
HF~
HG5
HG6
HMJXF
HQYDN
HRMNR
HVGLF
HZ~
I09
IHE
IJ-
IKXTQ
ITM
IWAJR
IXC
IZIGR
IZQ
I~X
I~Z
J-C
J0Z
JBSCW
JCJTX
JZLTJ
K7-
KDC
KOV
KOW
LAS
LLZTM
M4Y
MA-
N2Q
N9A
NB0
NDZJH
NPVJJ
NQJWS
NU0
O9-
O93
O9G
O9I
O9J
OAM
P19
P2P
P9O
PF0
PT4
PT5
QOK
QOS
R4E
R89
R9I
RHV
RIG
RNI
RNS
ROL
RPX
RSV
RZK
S16
S1Z
S26
S27
S28
S3B
SAP
SCJ
SCLPG
SCO
SDH
SDM
SHX
SISQX
SJYHP
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
SZN
T13
T16
TN5
TSG
TSK
TSV
TUC
U2A
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W23
W48
WK8
YLTOR
YOT
Z45
Z5O
Z7R
Z7S
Z7X
Z7Z
Z83
Z86
Z88
Z8M
Z8N
Z8R
Z8T
Z8W
Z92
ZMTXR
~EX
AAPKM
AAYXX
ABBRH
ABDBE
ABFSG
ABRTQ
ACSTC
ADHKG
ADKFA
AEZWR
AFDZB
AFFHD
AFHIU
AFOHR
AGQPQ
AHPBZ
AHWEU
AIXLP
ATHPR
AYFIA
CITATION
PHGZM
PHGZT
PQGLB
8FE
8FG
AZQEC
DWQXO
GNUQQ
JQ2
P62
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-c347t-8d29d7295f4ad4d223ef7c6bf7d00ae43e23f1cb3b2e254b1311d0757362d8323
IEDL.DBID P5Z
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001028383100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0178-2789
IngestDate Thu Nov 06 12:22:26 EST 2025
Wed Nov 05 08:56:56 EST 2025
Tue Nov 18 22:08:07 EST 2025
Sat Nov 29 02:23:31 EST 2025
Fri Feb 21 02:41:05 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords Deep learning
Loss function
Feature fusion
Stereo matching
Bilateral grid learning
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c347t-8d29d7295f4ad4d223ef7c6bf7d00ae43e23f1cb3b2e254b1311d0757362d8323
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
PQID 3033721959
PQPubID 2043737
PageCount 12
ParticipantIDs proquest_journals_3033880815
proquest_journals_3033721959
crossref_citationtrail_10_1007_s00371_023_03002_w
crossref_primary_10_1007_s00371_023_03002_w
springer_journals_10_1007_s00371_023_03002_w
PublicationCentury 2000
PublicationDate 2024-04-01
PublicationDateYYYYMMDD 2024-04-01
PublicationDate_xml – month: 04
  year: 2024
  text: 2024-04-01
  day: 01
PublicationDecade 2020
PublicationPlace Berlin/Heidelberg
PublicationPlace_xml – name: Berlin/Heidelberg
– name: Heidelberg
PublicationSubtitle International Journal of Computer Graphics
PublicationTitle The Visual computer
PublicationTitleAbbrev Vis Comput
PublicationYear 2024
Publisher Springer Berlin Heidelberg
Springer Nature B.V
Publisher_xml – name: Springer Berlin Heidelberg
– name: Springer Nature B.V
References CR38
CR36
Gharbi, Chen, Barron, Hasinoff, Durand (CR32) 2017; 36
CR35
CR34
CR33
CR31
CR30
Xu, Wang, Wang, Sheng, Deng (CR42) 2021; 28
Bao, Wang, Xu, Guo, Hong, Zhang (CR3) 2020; 63
Canny (CR49) 1986; 6
CR2
CR4
CR5
Yoo, Han (CR12) 2009; 28
Zhang, Lu, Lafruit (CR13) 2009; 19
CR9
CR48
CR47
CR46
CR45
Li, Fan, Lv, Ma (CR26) 2022; 38
CR44
CR43
CR41
CR40
Tang, Huang, Chen, Chen, Zhou, Zhang, Sun (CR8) 2023; 274
Hirschmuller (CR14) 2007; 30
Cheng, Zhong, Harandi, Dai, Chang, Li, Drummond, Ge (CR51) 2020; 33
CR19
CR18
CR17
CR15
CR54
Shankar, Tjersland, Ma, Stone, Bajracharya (CR53) 2022; 7
CR52
Tang, Zhou, Wang, Zhang (CR6) 2023; 211
CR50
Chen, Adams, Wadhwa, Hasinoff (CR39) 2016; 35
Chen, Paris, Durand (CR37) 2007; 26
Li, Zhang, Zhong, Wang (CR16) 2019; 35
CR29
CR28
Sun, Zheng, Shum (CR10) 2003; 25
CR27
CR25
CR24
Lin, Tang, Zou, Wang (CR7) 2021; 184
CR23
CR22
CR21
CR20
Deng, Yang, Lin, Tang (CR11) 2007; 29
Scharstein, Szeliski (CR1) 2002; 47
3002_CR36
3002_CR34
3002_CR35
X Cheng (3002_CR51) 2020; 33
3002_CR38
Y Li (3002_CR16) 2019; 35
J Chen (3002_CR39) 2016; 35
K Zhang (3002_CR13) 2009; 19
3002_CR33
3002_CR30
M Gharbi (3002_CR32) 2017; 36
3002_CR31
3002_CR25
K Shankar (3002_CR53) 2022; 7
3002_CR23
3002_CR24
3002_CR29
3002_CR27
Y Tang (3002_CR8) 2023; 274
3002_CR28
J-C Yoo (3002_CR12) 2009; 28
D Scharstein (3002_CR1) 2002; 47
3002_CR21
3002_CR22
3002_CR20
3002_CR15
J Canny (3002_CR49) 1986; 6
Y Deng (3002_CR11) 2007; 29
3002_CR18
3002_CR19
3002_CR17
G Lin (3002_CR7) 2021; 184
H Hirschmuller (3002_CR14) 2007; 30
Y Tang (3002_CR6) 2023; 211
J Sun (3002_CR10) 2003; 25
3002_CR9
3002_CR50
3002_CR4
3002_CR5
3002_CR54
3002_CR52
3002_CR2
3002_CR47
3002_CR48
3002_CR45
3002_CR46
J Chen (3002_CR37) 2007; 26
X Li (3002_CR26) 2022; 38
Q Xu (3002_CR42) 2021; 28
3002_CR40
W Bao (3002_CR3) 2020; 63
3002_CR43
3002_CR44
3002_CR41
References_xml – ident: CR45
– ident: CR22
– volume: 19
  start-page: 1073
  issue: 7
  year: 2009
  end-page: 1079
  ident: CR13
  article-title: Cross-based local stereo matching using orthogonal integral images
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2009.2020478
– volume: 36
  start-page: 1
  issue: 4
  year: 2017
  end-page: 12
  ident: CR32
  article-title: Deep bilateral learning for real-time image enhancement
  publication-title: ACM Trans. Graph. (TOG)
  doi: 10.1145/3072959.3073592
– ident: CR4
– volume: 63
  start-page: 1
  issue: 11
  year: 2020
  end-page: 11
  ident: CR3
  article-title: Instereo2k: a large real dataset for stereo matching in indoor scenes
  publication-title: Sci. China Inf. Sci.
  doi: 10.1007/s11432-019-2803-x
– volume: 29
  start-page: 1068
  issue: 6
  year: 2007
  end-page: 1079
  ident: CR11
  article-title: Stereo correspondence with occlusion handling in a symmetric patch-based graph-cuts model
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2007.1043
– ident: CR35
– ident: CR29
– ident: CR54
– ident: CR25
– ident: CR21
– ident: CR46
– ident: CR19
– volume: 35
  start-page: 1
  issue: 6
  year: 2016
  end-page: 8
  ident: CR39
  article-title: Bilateral guided upsampling
  publication-title: ACM Trans. Graph. (TOG)
  doi: 10.1145/2980179.2982423
– volume: 26
  start-page: 103
  issue: 3
  year: 2007
  ident: CR37
  article-title: Real-time edge-aware image processing with the bilateral grid
  publication-title: ACM Trans. Graph. (TOG)
  doi: 10.1145/1276377.1276506
– ident: CR15
– ident: CR50
– ident: CR9
– volume: 6
  start-page: 679
  year: 1986
  end-page: 698
  ident: CR49
  article-title: A computational approach to edge detection
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.1986.4767851
– volume: 47
  start-page: 7
  issue: 1
  year: 2002
  end-page: 42
  ident: CR1
  article-title: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms
  publication-title: Int. J. Comput. Vis.
  doi: 10.1023/A:1014573219977
– ident: CR36
– ident: CR5
– volume: 30
  start-page: 328
  issue: 2
  year: 2007
  end-page: 341
  ident: CR14
  article-title: Stereo processing by semiglobal matching and mutual information
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2007.1166
– ident: CR18
– ident: CR43
– ident: CR47
– volume: 38
  start-page: 3881
  issue: 11
  year: 2022
  end-page: 3895
  ident: CR26
  article-title: Area-based correlation and non-local attention network for stereo matching
  publication-title: Vis. Comput.
  doi: 10.1007/s00371-021-02228-w
– volume: 35
  start-page: 257
  year: 2019
  end-page: 269
  ident: CR16
  article-title: An efficient stereo matching based on fragment matching
  publication-title: Vis. Comput.
  doi: 10.1007/s00371-018-1491-0
– ident: CR2
– ident: CR30
– volume: 28
  start-page: 819
  issue: 6
  year: 2009
  end-page: 843
  ident: CR12
  article-title: Fast normalized cross-correlation
  publication-title: Circ. Syst. Signal Process.
  doi: 10.1007/s00034-009-9130-7
– ident: CR33
– volume: 211
  year: 2023
  ident: CR6
  article-title: Fruit detection and positioning technology for a C. Abel orchard based on improved yolov4-tiny model and binocular stereo vision
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2022.118573
– volume: 25
  start-page: 787
  issue: 7
  year: 2003
  end-page: 800
  ident: CR10
  article-title: Stereo matching using belief propagation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2003.1206509
– ident: CR40
– ident: CR27
– ident: CR23
– volume: 28
  start-page: 613
  year: 2021
  end-page: 617
  ident: CR42
  article-title: Deep bilateral learning for stereo image super-resolution
  publication-title: IEEE Signal Process. Lett.
  doi: 10.1109/LSP.2021.3066125
– volume: 274
  year: 2023
  ident: CR8
  article-title: Novel visual crack width measurement based on backbone double-scale features for improved detection automation
  publication-title: Eng. Struct.
  doi: 10.1016/j.engstruct.2022.115158
– ident: CR44
– ident: CR48
– volume: 7
  start-page: 2305
  issue: 2
  year: 2022
  end-page: 2312
  ident: CR53
  article-title: A learned stereo depth system for robotic manipulation in homes
  publication-title: IEEE Robot. Autom. Lett.
  doi: 10.1109/LRA.2022.3143895
– ident: CR38
– ident: CR52
– ident: CR17
– ident: CR31
– volume: 33
  start-page: 22158
  year: 2020
  end-page: 22169
  ident: CR51
  article-title: Hierarchical neural architecture search for deep stereo matching
  publication-title: Adv. Neural. Inf. Process. Syst.
– ident: CR34
– volume: 184
  year: 2021
  ident: CR7
  article-title: Three-dimensional reconstruction of guava fruits and branches using instance segmentation and geometry analysis
  publication-title: Comput. Electron. Agric.
  doi: 10.1016/j.compag.2021.106107
– ident: CR28
– ident: CR41
– ident: CR24
– ident: CR20
– ident: 3002_CR34
  doi: 10.1109/CVPR.2019.00339
– ident: 3002_CR36
  doi: 10.1109/ICCV.2019.00448
– ident: 3002_CR33
  doi: 10.1109/ICCV.2015.316
– volume: 26
  start-page: 103
  issue: 3
  year: 2007
  ident: 3002_CR37
  publication-title: ACM Trans. Graph. (TOG)
  doi: 10.1145/1276377.1276506
– ident: 3002_CR29
  doi: 10.1109/CVPR.2018.00920
– volume: 28
  start-page: 819
  issue: 6
  year: 2009
  ident: 3002_CR12
  publication-title: Circ. Syst. Signal Process.
  doi: 10.1007/s00034-009-9130-7
– volume: 35
  start-page: 257
  year: 2019
  ident: 3002_CR16
  publication-title: Vis. Comput.
  doi: 10.1007/s00371-018-1491-0
– ident: 3002_CR23
  doi: 10.1109/CVPR52688.2022.01264
– ident: 3002_CR31
  doi: 10.1109/CVPR42600.2020.00203
– volume: 19
  start-page: 1073
  issue: 7
  year: 2009
  ident: 3002_CR13
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2009.2020478
– volume: 35
  start-page: 1
  issue: 6
  year: 2016
  ident: 3002_CR39
  publication-title: ACM Trans. Graph. (TOG)
  doi: 10.1145/2980179.2982423
– volume: 7
  start-page: 2305
  issue: 2
  year: 2022
  ident: 3002_CR53
  publication-title: IEEE Robot. Autom. Lett.
  doi: 10.1109/LRA.2022.3143895
– volume: 28
  start-page: 613
  year: 2021
  ident: 3002_CR42
  publication-title: IEEE Signal Process. Lett.
  doi: 10.1109/LSP.2021.3066125
– volume: 33
  start-page: 22158
  year: 2020
  ident: 3002_CR51
  publication-title: Adv. Neural. Inf. Process. Syst.
– volume: 38
  start-page: 3881
  issue: 11
  year: 2022
  ident: 3002_CR26
  publication-title: Vis. Comput.
  doi: 10.1007/s00371-021-02228-w
– ident: 3002_CR41
  doi: 10.1109/CVPR46437.2021.01592
– ident: 3002_CR44
  doi: 10.5194/isprsannals-II-3-W5-427-2015
– ident: 3002_CR54
  doi: 10.1109/CVPR46437.2021.00539
– ident: 3002_CR21
  doi: 10.1109/CVPR.2019.00027
– ident: 3002_CR24
  doi: 10.1109/WACV51458.2022.00075
– ident: 3002_CR4
  doi: 10.1007/978-3-319-11752-2_3
– ident: 3002_CR45
  doi: 10.1007/978-3-030-01234-2_39
– volume: 29
  start-page: 1068
  issue: 6
  year: 2007
  ident: 3002_CR11
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2007.1043
– ident: 3002_CR30
  doi: 10.1109/ICCV.2017.324
– ident: 3002_CR40
  doi: 10.1109/ICCV48922.2021.00441
– ident: 3002_CR27
  doi: 10.1109/CRV.2014.56
– ident: 3002_CR38
  doi: 10.1007/11744085_44
– volume: 63
  start-page: 1
  issue: 11
  year: 2020
  ident: 3002_CR3
  publication-title: Sci. China Inf. Sci.
  doi: 10.1007/s11432-019-2803-x
– volume: 184
  year: 2021
  ident: 3002_CR7
  publication-title: Comput. Electron. Agric.
  doi: 10.1016/j.compag.2021.106107
– ident: 3002_CR28
– ident: 3002_CR18
  doi: 10.1109/CVPR.2016.438
– volume: 47
  start-page: 7
  issue: 1
  year: 2002
  ident: 3002_CR1
  publication-title: Int. J. Comput. Vis.
  doi: 10.1023/A:1014573219977
– ident: 3002_CR25
  doi: 10.1609/aaai.v36i2.20056
– ident: 3002_CR19
  doi: 10.1109/CVPR.2018.00567
– ident: 3002_CR5
  doi: 10.1109/IVS.2013.6629487
– volume: 36
  start-page: 1
  issue: 4
  year: 2017
  ident: 3002_CR32
  publication-title: ACM Trans. Graph. (TOG)
  doi: 10.1145/3072959.3073592
– volume: 6
  start-page: 679
  year: 1986
  ident: 3002_CR49
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.1986.4767851
– ident: 3002_CR20
  doi: 10.1109/ICCVW.2017.108
– volume: 211
  year: 2023
  ident: 3002_CR6
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2022.118573
– volume: 30
  start-page: 328
  issue: 2
  year: 2007
  ident: 3002_CR14
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2007.1166
– ident: 3002_CR2
  doi: 10.1109/CVPR.2012.6248074
– ident: 3002_CR50
– volume: 274
  year: 2023
  ident: 3002_CR8
  publication-title: Eng. Struct.
  doi: 10.1016/j.engstruct.2022.115158
– volume: 25
  start-page: 787
  issue: 7
  year: 2003
  ident: 3002_CR10
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2003.1206509
– ident: 3002_CR46
  doi: 10.1007/978-3-030-20873-8_2
– ident: 3002_CR17
  doi: 10.1109/CVPR.2015.7298767
– ident: 3002_CR22
  doi: 10.1109/ICCV.2017.17
– ident: 3002_CR35
  doi: 10.1007/978-3-030-01267-0_35
– ident: 3002_CR52
  doi: 10.1109/ICRA40945.2020.9197031
– ident: 3002_CR47
  doi: 10.1609/aaai.v34i07.6991
– ident: 3002_CR15
  doi: 10.1109/CVPRW.2010.5543769
– ident: 3002_CR48
  doi: 10.1109/ICASSP.2018.8461664
– ident: 3002_CR9
  doi: 10.1109/ICCV.2001.937668
– ident: 3002_CR43
  doi: 10.1109/CVPR.2016.90
SSID ssj0017749
Score 2.3795638
Snippet Deep learning-based stereo matching has made significant progress, but it still faces challenges: The disparity prediction error maps of current models show...
SourceID proquest
crossref
springer
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 2975
SubjectTerms Accuracy
Algorithms
Artificial Intelligence
Computer Graphics
Computer Science
Deep learning
Design
Embedding
Frames per second
Image Processing and Computer Vision
Matching
Neural networks
Original Article
Real time
SummonAdditionalLinks – databaseName: Springer Online Journals
  dbid: RSV
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwED5BYYCBQgFRKMgDG1hK7aR2mHiIiqlCFFC3KPFDQqpa1BT69zm7SQqIIsFsJ7HOj--7nO8-gNPIiihjAacGwY2GYeDiu2lGpdS8I5lGL8N6sQnR68nBIL4vksLy8rZ7GZL0J3WV7Oary1HEGIoLE_fxbBXWEO6kE2x46D9XsQMkNJ70ttE_cnmeRarMz-_4CkcLjvktLOrRplv_3zi3Yatgl-Rqvhx2YMWMGlAvlRtIsZEbsPmpDOEuXN5e97HZjC-I-7tGHbJpMsTxEgd7buoIcluC_HJInRg9yX13gmzXX8Xcg6fu7ePNHS2UFajioZhSqVmskVZHNkx1qJEiGCtUJ7NCB0FqQm4Yt22V8YwZ9CAzV5NHI7kQCHcazwC-D7XReGQOgKTCslhFPIuRWmlmUoMHprUKsVGZKI2a0C4NnKii7LhTvxgmVcFkb7AEDZZ4gyWzJpxVz7zOi2782rtVzltSbMA8QWTm6NzGUby0WTrRERzfeTmNi-blHzv8W_cj2GDIguZXfVpQm07ezDGsq_fpSz458ev2A3JO5Us
  priority: 102
  providerName: Springer Nature
Title EBStereo: edge-based loss function for real-time stereo matching
URI https://link.springer.com/article/10.1007/s00371-023-03002-w
https://www.proquest.com/docview/3033721959
https://www.proquest.com/docview/3033880815
Volume 40
WOSCitedRecordID wos001028383100002&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: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1432-2315
  dateEnd: 20241213
  omitProxy: false
  ssIdentifier: ssj0017749
  issn: 0178-2789
  databaseCode: P5Z
  dateStart: 19970201
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 1432-2315
  dateEnd: 20241213
  omitProxy: false
  ssIdentifier: ssj0017749
  issn: 0178-2789
  databaseCode: K7-
  dateStart: 19970201
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1432-2315
  dateEnd: 20241213
  omitProxy: false
  ssIdentifier: ssj0017749
  issn: 0178-2789
  databaseCode: BENPR
  dateStart: 19970201
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: Springer Online Journals
  customDbUrl:
  eissn: 1432-2315
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017749
  issn: 0178-2789
  databaseCode: RSV
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3PT8IwFH4R8KAHfxtRJD1408bRbmzzomIgJiaEgBriZdn6IzEhgAzl3_e1bKAmcPGyS7e06eve972-9n0AF572vYQ5nCoEN-q6jsnvxgkNAsnrAZMYZWgrNuG320G_H3ayDbc0O1aZ-0TrqOVImD3ya3S1HKOV0Atvxx_UqEaZ7GomoVGAkqmSYKQbOt7bIouA1MbS3xpGSubGZ3Zpxl6ds7XqKCIWxWWOXmH2G5iWbPNPgtTiTmv3vyPeg52McZL7-RLZhw01PIDtH3UID-Gu2ejh_KrRDTHba9RAmyQDHCYxuGdsR5DcEiSYA2rU6ElqXydId-1ZzCN4aTWfHx5pJq1ABXf9KQ0kCyXyak-7sXQlcgSlfVFPtC8dJ1YuV4zrmkh4whSGkIkpyiORXfiIdxKdAD-G4nA0VCdAYl-zUHg8CZFbSaZihR5Ta4HgKJQXe2Wo5fMaiazuuJG_GESLisnWFhHaIrK2iGZluFx8M55X3Vj7diU3QJT9gWm0nP2VzYFRHcHxXeUWXjav7ux0fWdnsMWQ9szP9lSgOJ18qnPYFF_T93RShVKj2e50q1B48mnVLlZ8dnuv3-X47A4
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3JTsMwEB2xScCBHVFWH-AEFq2d1AkSYi0CFSokQOIWEi9SpdKWtlDxU3wjYzdpAYneOHC2Eyee8bw3tmcGYNs3wk9YnlON4EY9L2_Pd-OEBoHixYAp9DKMKzYhKpXg8TG8HYGPLBbGXqvMbKIz1Koh7R75Pppajt5K6IdHzRdqq0bZ09WshEZPLcr6vYsuW_vw6hzlu8PYRen-7JKmVQWo5J7o0ECxUCGl9I0XK08hPGojZDExQuXzsfa4ZtwUZMITptF7Smw-GoXAKtDUK9R_ju8dhXGPB8Kuq7Kg_VMLpFKObhfQM7MRpmmQjgvVc7nxKCIkxWWFVqj7HQgH7PbHgazDuYvZ_zZDczCTMmpy0lsC8zCi6wsw_SXP4iIcl07vUH9044DY7UNqoVuRGk4LsbhudZMgeSdIoGu0U33WpO26E6Tz7q7pEjz8yS8sw1i9UdcrQGJhWCh9noTIHRXTsUZEMEYi-Evtx34OCpkcI5nmVbflPWpRPyO0k32Eso-c7KNuDnb7zzR7WUWG9l7PBB6lFqYdDaT9a3Ngq6rg9-1lGjVo_n2w1eGDbcHk5f3NdXR9VSmvwRRDite7x7QOY53Wq96ACfnWqbZbm25pEHj6a037BIDqRCA
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwFD7oFNEHp1NxOjUPvmmwa9q19cnbhqKMwVT2FtomAWFsY6vu73uSXjbFCeJz0jack-T7Ts8N4NRVnhvZFqMSwY06jqX9u2FEfV-whm8LtDKUaTbhtdt-rxd05rL4TbR77pJMcxp0laZBcjES6qJIfDOV5ijiDcVNimd6ugwrjg6k1_Z697XwIyC5MQS4jraSzvnM0mZ-fsdXaJrxzW8uUoM8rfL_17wFmxnrJNfpNtmGJTmoQDnv6ECyA16BjbnyhDtw1bzp4rAcXhL9141qxBOkj2snGg61SglyXoK8s091k3oyMdMJsmATorkLL63m8-09zTou0Jg5XkJ9YQcC6barnFA4AqmDVF7ciJQnLCuUDpM2U_U4YpEt0bKMdK0egaTDQxgUeDewPSgNhgO5DyT0lB3ELosCpFzClqHEi1SpGDEzlm7oVqGeC5vHWTly3RWjz4tCykZgHAXGjcD4tApnxTOjtBjHr7NruQ55djAnHBGbodEbuMHCYV83I8H1necqnQ0v_tjB36afwFrnrsWfHtqPh7BuI1FKo4FqUErG7_IIVuOP5G0yPjbb-RObsPET
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=EBStereo%3A+edge-based+loss+function+for+real-time+stereo+matching&rft.jtitle=The+Visual+computer&rft.au=Bi%2C+Weijie&rft.au=Chen%2C+Ming&rft.au=Wu%2C+Dongliu&rft.au=Lu%2C+Shenglian&rft.date=2024-04-01&rft.issn=0178-2789&rft.eissn=1432-2315&rft.volume=40&rft.issue=4&rft.spage=2975&rft.epage=2986&rft_id=info:doi/10.1007%2Fs00371-023-03002-w&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s00371_023_03002_w
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0178-2789&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0178-2789&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0178-2789&client=summon