Scalable Surface Reconstruction with Delaunay‐Graph Neural Networks

We introduce a novel learning‐based, visibility‐aware, surface reconstruction method for large‐scale, defect‐laden point clouds. Our approach can cope with the scale and variety of point cloud defects encountered in real‐life Multi‐View Stereo (MVS) acquisitions. Our method relies on a 3D Delaunay t...

Full description

Saved in:

Bibliographic Details
Published in:	Computer graphics forum Vol. 40; no. 5; pp. 157 - 167
Main Authors:	Sulzer, R., Landrieu, L., Marlet, R., Vallet, B.
Format:	Journal Article
Language:	English
Published:	Oxford Blackwell Publishing Ltd 01.08.2021 Wiley
Series:	Eurographics Symposium on Geometry Processing 2021, July 12 – 14, 2021
Subjects:	Algorithms CCS Concepts Computer Science Computing methodologies → Reconstruction Deep learning Graph neural networks Machine learning Neural networks Reconstruction Shape inference Visibility
ISSN:	0167-7055, 1467-8659
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	We introduce a novel learning‐based, visibility‐aware, surface reconstruction method for large‐scale, defect‐laden point clouds. Our approach can cope with the scale and variety of point cloud defects encountered in real‐life Multi‐View Stereo (MVS) acquisitions. Our method relies on a 3D Delaunay tetrahedralization whose cells are classified as inside or outside the surface by a graph neural network and an energy model solvable with a graph cut. Our model, making use of both local geometric attributes and line‐of‐sight visibility information, is able to learn a visibility model from a small amount of synthetic training data and generalizes to real‐life acquisitions. Combining the efficiency of deep learning methods and the scalability of energy‐based models, our approach outperforms both learning and non learning‐based reconstruction algorithms on two publicly available reconstruction benchmarks.
AbstractList	We introduce a novel learning‐based, visibility‐aware, surface reconstruction method for large‐scale, defect‐laden point clouds. Our approach can cope with the scale and variety of point cloud defects encountered in real‐life Multi‐View Stereo (MVS) acquisitions. Our method relies on a 3D Delaunay tetrahedralization whose cells are classified as inside or outside the surface by a graph neural network and an energy model solvable with a graph cut. Our model, making use of both local geometric attributes and line‐of‐sight visibility information, is able to learn a visibility model from a small amount of synthetic training data and generalizes to real‐life acquisitions. Combining the efficiency of deep learning methods and the scalability of energy‐based models, our approach outperforms both learning and non learning‐based reconstruction algorithms on two publicly available reconstruction benchmarks.
Author	Vallet, B. Marlet, R. Landrieu, L. Sulzer, R.
Author_xml	– sequence: 1 givenname: R. orcidid: 0000-0003-1707-7621 surname: Sulzer fullname: Sulzer, R. organization: Univ Gustave Eiffel, CNRS – sequence: 2 givenname: L. orcidid: 0000-0002-7738-8141 surname: Landrieu fullname: Landrieu, L. organization: Univ Gustave Eiffel, ENSG IGN – sequence: 3 givenname: R. orcidid: 0000-0003-1612-1758 surname: Marlet fullname: Marlet, R. organization: valeo.ai – sequence: 4 givenname: B. orcidid: 0000-0002-9492-5180 surname: Vallet fullname: Vallet, B. organization: Univ Gustave Eiffel, ENSG IGN
BackLink	https://hal.science/hal-03312448$$DView record in HAL
BookMark	eNp9kM9KAzEQxoMo2FYPvsGCJw9tk82fTY-l9o9QFKyew2w2a7fG3ZrsWnrzEXxGn8TUioKgc_mG4Ztvhl8bHZZVaRA6I7hHQvX1Q94jjAp2gFqEiaQrBR8cohYmoU8w58eo7f0KY8wSwVtovNBgIbUmWjQuB22iW6Or0teu0XVRldGmqJfRpbHQlLB9f32bOlgvo2vTOLBB6k3lHv0JOsrBenP6pR10PxnfjWbd-c30ajScdzWlhHUznSaxAEN4TIHIgeY401pQoAKDjFMjs9ykmkojOWMZAM-o0YMMA6OGyYx20MU-dwlWrV3xBG6rKijUbDhXuxkOd2LG5AsJ3vO9d-2q58b4Wq2qxpXhPRVzQTmWhMmfRO0q753Jv2MJVjuiKhBVn0SDt__Lq4sadpRqB4X9b2NTWLP9O1qNppP9xgeyyImo
CitedBy_id	crossref_primary_10_14358_PERS_23_00007R3 crossref_primary_10_1109_TVCG_2023_3281781 crossref_primary_10_3390_electronics14152949 crossref_primary_10_1016_j_cad_2024_103729 crossref_primary_10_1007_s11263_024_02344_9 crossref_primary_10_1109_TPAMI_2024_3510932 crossref_primary_10_1080_10095020_2025_2502481 crossref_primary_10_1145_3687956
Cites_doi	10.1111/cgf.12431 10.1109/CVPR.2017.272 10.1109/CVPR.2010.5539824 10.1111/j.1467-8659.2009.01530.x 10.1145/1576246.1531330 10.1109/CVPR42600.2020.00264 10.1007/978-3-030-58598-3_5 10.1007/978-3-319-54190-7_23 10.1016/j.cagd.2004.09.004 10.1109/CVPR.2017.11 10.1109/CVPR.2019.01037 10.1109/CVPR.2019.00025 10.1109/CVPR.2018.00029 10.1155/2014/798595 10.1109/CVPR.2019.00459 10.1007/978-3-030-58526-6_36 10.1109/TPAMI.2004.60 10.1007/978-3-030-58592-1_45 10.1109/CVPR42600.2020.00105 10.1109/CVPR.2011.5995693 10.3390/s19061278 10.1109/34.969114 10.1109/CVPR.2018.00030 10.1109/ICCV.2019.00988 10.1109/ICPR.2016.7900128 10.1109/CVPR.2019.00572 10.1007/978-3-319-10602-1_54 10.1007/978-3-319-46484-8_38 10.1145/3386569.3392415
ContentType	Journal Article
Copyright	2021 The Author(s) Computer Graphics Forum © 2021 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd. 2021 The Eurographics Association and John Wiley & Sons Ltd. Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml	– notice: 2021 The Author(s) Computer Graphics Forum © 2021 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd. – notice: 2021 The Eurographics Association and John Wiley & Sons Ltd. – notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID	AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D 1XC VOOES
DOI	10.1111/cgf.14364
DatabaseName	CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle	CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional
DatabaseTitleList	CrossRef Computer and Information Systems Abstracts
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1467-8659
EndPage	167
ExternalDocumentID	oai:HAL:hal-03312448v1 10_1111_cgf_14364 CGF14364
Genre	article
GrantInformation_xml	– fundername: BIOM funderid: ANR-17-CE23-0003
GroupedDBID	.3N .4S .DC .GA .Y3 05W 0R~ 10A 15B 1OB 1OC 29F 31~ 33P 3SF 4.4 50Y 50Z 51W 51X 52M 52N 52O 52P 52S 52T 52U 52W 52X 5GY 5HH 5LA 5VS 66C 6J9 702 7PT 8-0 8-1 8-3 8-4 8-5 8UM 8VB 930 A03 AAESR AAEVG AAHHS AAHQN AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCQN ABCUV ABDBF ABDPE ABEML ABPVW ACAHQ ACBWZ ACCFJ ACCZN ACFBH ACGFS ACPOU ACRPL ACSCC ACUHS ACXBN ACXQS ACYXJ ADBBV ADEOM ADIZJ ADKYN ADMGS ADNMO ADOZA ADXAS ADZMN ADZOD AEEZP AEGXH AEIGN AEIMD AEMOZ AENEX AEQDE AEUQT AEUYR AFBPY AFEBI AFFNX AFFPM AFGKR AFPWT AFWVQ AFZJQ AHBTC AHEFC AHQJS AITYG AIURR AIWBW AJBDE AJXKR AKVCP ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ARCSS ASPBG ATUGU AUFTA AVWKF AZBYB AZFZN AZVAB BAFTC BDRZF BFHJK BHBCM BMNLL BMXJE BNHUX BROTX BRXPI BY8 CAG COF CS3 CWDTD D-E D-F DCZOG DPXWK DR2 DRFUL DRSTM DU5 EAD EAP EBA EBO EBR EBS EBU EDO EJD EMK EST ESX F00 F01 F04 F5P FEDTE FZ0 G-S G.N GODZA H.T H.X HF~ HGLYW HVGLF HZI HZ~ I-F IHE IX1 J0M K1G K48 LATKE LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES MEWTI MK4 MRFUL MRSTM MSFUL MSSTM MXFUL MXSTM N04 N05 N9A NF~ O66 O9- OIG P2W P2X P4D PALCI PQQKQ Q.N Q11 QB0 QWB R.K RDJ RIWAO RJQFR ROL RX1 SAMSI SUPJJ TH9 TN5 TUS UB1 V8K W8V W99 WBKPD WIH WIK WOHZO WQJ WRC WXSBR WYISQ WZISG XG1 ZL0 ZZTAW ~IA ~IF ~WT AAMMB AAYXX ADMLS AEFGJ AEYWJ AGHNM AGQPQ AGXDD AGYGG AIDQK AIDYY AIQQE CITATION O8X 7SC 8FD JQ2 L7M L~C L~D 1XC VOOES
ID	FETCH-LOGICAL-c3314-dcb726ae1523a189c50dcc63a360a82be8dfebc38e8544daa5d3ec9d0a43e48d3
IEDL.DBID	DRFUL
ISICitedReferencesCount	10
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000687373500014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0167-7055
IngestDate	Sun Oct 19 06:20:39 EDT 2025 Fri Jul 25 06:31:19 EDT 2025 Sat Nov 29 03:41:20 EST 2025 Tue Nov 18 21:11:20 EST 2025 Wed Jan 22 16:57:05 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	5
Language	English
License	Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c3314-dcb726ae1523a189c50dcc63a360a82be8dfebc38e8544daa5d3ec9d0a43e48d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-1612-1758 0000-0002-9492-5180 0000-0003-1707-7621 0000-0002-7738-8141
OpenAccessLink	https://hal.science/hal-03312448
PQID	2563508148
PQPubID	30877
PageCount	11
ParticipantIDs	hal_primary_oai_HAL_hal_03312448v1 proquest_journals_2563508148 crossref_primary_10_1111_cgf_14364 crossref_citationtrail_10_1111_cgf_14364 wiley_primary_10_1111_cgf_14364_CGF14364
PublicationCentury	2000
PublicationDate	August 2021 2021-08-00 20210801 2021-08
PublicationDateYYYYMMDD	2021-08-01
PublicationDate_xml	– month: 08 year: 2021 text: August 2021
PublicationDecade	2020
PublicationPlace	Oxford
PublicationPlace_xml	– name: Oxford
PublicationSeriesTitle	Eurographics Symposium on Geometry Processing 2021, July 12 – 14, 2021
PublicationTitle	Computer graphics forum
PublicationYear	2021
Publisher	Blackwell Publishing Ltd Wiley
Publisher_xml	– name: Blackwell Publishing Ltd – name: Wiley
References	2001 2012 2011 2021 2010 2020 2009 2019 2018 2017 2016 2004 2015 2014 2013 2005; 22 e_1_2_7_5_2 e_1_2_7_4_2 e_1_2_7_3_2 e_1_2_7_2_2 e_1_2_7_9_2 e_1_2_7_8_2 e_1_2_7_7_2 e_1_2_7_6_2 e_1_2_7_19_2 e_1_2_7_18_2 e_1_2_7_17_2 e_1_2_7_16_2 e_1_2_7_15_2 e_1_2_7_14_2 e_1_2_7_40_2 e_1_2_7_13_2 e_1_2_7_41_2 e_1_2_7_12_2 e_1_2_7_42_2 e_1_2_7_11_2 e_1_2_7_43_2 e_1_2_7_10_2 e_1_2_7_44_2 e_1_2_7_45_2 e_1_2_7_26_2 e_1_2_7_27_2 e_1_2_7_28_2 e_1_2_7_29_2 e_1_2_7_25_2 e_1_2_7_24_2 e_1_2_7_30_2 e_1_2_7_23_2 e_1_2_7_31_2 e_1_2_7_22_2 e_1_2_7_32_2 e_1_2_7_21_2 e_1_2_7_33_2 e_1_2_7_20_2 e_1_2_7_34_2 e_1_2_7_35_2 e_1_2_7_36_2 e_1_2_7_37_2 e_1_2_7_38_2 e_1_2_7_39_2
References_xml	– year: 2011 – volume: 22 start-page: 121 issue: 2 year: 2005 end-page: 146 article-title: Estimating differential quantities using polynomial fitting of osculating jets publication-title: Computer Aided Geometric Design – year: 2009 – year: 2001 – year: 2020 – year: 2021 – year: 2004 – year: 2017 – year: 2016 – year: 2018 – year: 2019 – year: 2014 – year: 2015 – year: 2010 – year: 2013 – year: 2012 – ident: e_1_2_7_4_2 doi: 10.1111/cgf.12431 – ident: e_1_2_7_40_2 doi: 10.1109/CVPR.2017.272 – ident: e_1_2_7_15_2 doi: 10.1109/CVPR.2010.5539824 – ident: e_1_2_7_31_2 doi: 10.1111/j.1467-8659.2009.01530.x – ident: e_1_2_7_8_2 doi: 10.1145/1576246.1531330 – ident: e_1_2_7_41_2 – ident: e_1_2_7_13_2 – ident: e_1_2_7_30_2 – ident: e_1_2_7_24_2 – ident: e_1_2_7_32_2 – ident: e_1_2_7_2_2 doi: 10.1109/CVPR42600.2020.00264 – ident: e_1_2_7_18_2 – ident: e_1_2_7_33_2 doi: 10.1007/978-3-030-58598-3_5 – ident: e_1_2_7_11_2 doi: 10.1007/978-3-319-54190-7_23 – ident: e_1_2_7_6_2 – ident: e_1_2_7_16_2 doi: 10.1016/j.cagd.2004.09.004 – ident: e_1_2_7_26_2 – ident: e_1_2_7_38_2 doi: 10.1109/CVPR.2017.11 – ident: e_1_2_7_9_2 – ident: e_1_2_7_12_2 – ident: e_1_2_7_43_2 doi: 10.1109/CVPR.2019.01037 – ident: e_1_2_7_36_2 doi: 10.1109/CVPR.2019.00025 – ident: e_1_2_7_44_2 doi: 10.1109/CVPR.2018.00029 – ident: e_1_2_7_28_2 doi: 10.1155/2014/798595 – ident: e_1_2_7_35_2 doi: 10.1109/CVPR.2019.00459 – ident: e_1_2_7_14_2 doi: 10.1007/978-3-030-58526-6_36 – ident: e_1_2_7_37_2 – ident: e_1_2_7_29_2 – ident: e_1_2_7_5_2 doi: 10.1109/TPAMI.2004.60 – ident: e_1_2_7_39_2 doi: 10.1007/978-3-030-58592-1_45 – ident: e_1_2_7_3_2 – ident: e_1_2_7_34_2 doi: 10.1109/CVPR42600.2020.00105 – ident: e_1_2_7_22_2 – ident: e_1_2_7_27_2 doi: 10.1109/CVPR.2011.5995693 – ident: e_1_2_7_25_2 – ident: e_1_2_7_45_2 doi: 10.3390/s19061278 – ident: e_1_2_7_10_2 doi: 10.1109/34.969114 – ident: e_1_2_7_20_2 doi: 10.1109/CVPR.2018.00030 – ident: e_1_2_7_21_2 doi: 10.1109/ICCV.2019.00988 – ident: e_1_2_7_7_2 doi: 10.1109/ICPR.2016.7900128 – ident: e_1_2_7_19_2 doi: 10.1109/CVPR.2019.00572 – ident: e_1_2_7_42_2 doi: 10.1007/978-3-319-10602-1_54 – ident: e_1_2_7_17_2 doi: 10.1007/978-3-319-46484-8_38 – ident: e_1_2_7_23_2 doi: 10.1145/3386569.3392415
SSID	ssj0004765
Score	2.39477
Snippet	We introduce a novel learning‐based, visibility‐aware, surface reconstruction method for large‐scale, defect‐laden point clouds. Our approach can cope with the... We introduce a novel learning-based, visibility-aware, surface reconstruction method for large-scale, defect-laden point clouds. Our approach can cope with the...
SourceID	hal proquest crossref wiley
SourceType	Open Access Repository Aggregation Database Enrichment Source Index Database Publisher
StartPage	157
SubjectTerms	Algorithms CCS Concepts Computer Science Computing methodologies → Reconstruction Deep learning Graph neural networks Machine learning Neural networks Reconstruction Shape inference Visibility
Title	Scalable Surface Reconstruction with Delaunay‐Graph Neural Networks
URI	https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.14364 https://www.proquest.com/docview/2563508148 https://hal.science/hal-03312448
Volume	40
WOSCitedRecordID	wos000687373500014&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: PRVWIB databaseName: Wiley Online Library - Journals customDbUrl: eissn: 1467-8659 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004765 issn: 0167-7055 databaseCode: DRFUL dateStart: 19970101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5q60EPvsVqlSAevASa7CbZ4Kn0oYdSxAd4C5PZiQpSxdqCN3-Cv9Ff4m6a1AoKgreQTJLNPDIzy8w3AEesY8p8j1wvYnZlRuiiUOzGKg0oixBTzqeW9KPBQN3cxOcVOCl7Yab4ELMNN2sZ-f_aGjimozkjp9vMmLkI5QLUbFOVUela56J33f9qi4zCoIT2tqAxBbCQLeSZ3fzNHS3c2WLIuUhzPl7NHU5v9V9LXYOVIs50WlPFWIcKDzdgeQ59cBO6l0Y-tnPKuRw_Z0js2Fz0C1HWsXu0TocfcDzE14-391MLbu1YOA_z5MG0fny0Bde97lX7zC2mKrgkhCddTWnkh8jGcQv0VExBUxOFAkXYROWnrHTGKRmBqUBKjRhowRTrJkrBUmmxDdXh45B3wAmIMtJBoCJWkjSmkr0QhXX60teo63BcMjehAnLcTr54SMrUw3AmyTlTh8MZ6dMUZ-NHIiOh2XWLjH3W6if2XNN8m4lU1MSrQ6MUYFLY4ygxgZ0woajJ_cyaclH9_pakfdrLD3b_TroHS74tdskrAxtQNZLifVikycv96PmgUMxPMV7n5Q
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dS9xAEB_0TrB98KNaenpqKD74Ekiym2QDvsh9iulReif4FiazEy3ItXhV6Fv_hP6N_UvczSXnCQoF30IySTbzkZlZZn4DcMw6oSLwyfVjZlcWhC4KxW6i8pCKGDHncmpJGo9G6uoq-boCp3UvzBwfYrHhZi2j_F9bA7cb0ktWTteFsXMRyVVoSqNGXgOa3W_9y_SpLzKOwhrb26LGVMhCtpJncfMzf7R6Y6shl0LN5YC19Dj9zbetdQs2qkjTOZurxjas8PQDvF_CH9yB3thIyPZOOeP7uwKJHZuNPmHKOnaX1unyLd5P8fe_P38HFt7asYAe5smjeQX5bBcu-71JZ-hWcxVcEsKXrqY8DiJk47oF-iqh0NNEkUAReaiCnJUuOCcjMhVKqRFDLZgS7aEULJUWH6Ex_THlT-CERAXpMFQxK0kac8l-hMK6fRlo1C04qbmbUQU6bmdf3GZ18mE4k5WcacHnBenPOdLGi0RGRIvrFht7eJZm9pxnvs3EKurBb0G7lmBWWeQsM6GdMMGoyf7MmkpZvf6WrDPolwd7_096BOvDyZc0S89HF_vwLrClL2WdYBsaRmp8AGv08Ov77O6w0tJH-4zrzA
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NattAEB4cu4T2kP4kpW6cVJQeehFY2l1pBb2EOIpDhTF1DbmJ0ewoKQQ3xE2gtz5CnzFPkl1ZslVoIdCbkEbSamZH880y-w3ABzYJlWFAfhAz-7Ik9FFo9hNdKCpjxIKrriVZPJno8_Nk2oFPzV6YFT_EesHNeUb1v3YOztembHk5XZTWz0Ukt6AnlcX5XeiNvqTzbLMvMo5Uw-3tWGNqZiFXybO--Y94tHXpqiFbULMNWKuIkz7_v7G-gJ0aaXpHq6nxEjq8eAXPWvyDu3AysxZye6e82e1NicSey0Y3nLKeW6X1RnyFtwv8ef_r96mjt_YcoYd98mRVQb7cg3l68vV47Nd9FXwSIpC-oSIOI2QbugUGOiE1NESRQBENUYcFa1NyQdZkWklpEJURTIkZohQstRGvobv4vuA34CmikoxSOmYtyWAhOYhQuLAvQ4OmDx8b7eZUk4673hdXeZN8WM3klWb68H4ter1i2virkDXR-rrjxh4fZbk7N7TfZrGKvgv6MGgsmNceucwttBMWjNrsz46pstW_35Ifn6bVwdvHi76D7ekozbOzyed9eBq6ypeqTHAAXWs0PoAndPfj2_LmsJ6kD72K61A
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=Scalable+Surface+Reconstruction+with+Delaunay%E2%80%90Graph+Neural+Networks&rft.jtitle=Computer+graphics+forum&rft.au=Sulzer%2C+R.&rft.au=Landrieu%2C+L.&rft.au=Marlet%2C+R.&rft.au=Vallet%2C+B.&rft.date=2021-08-01&rft.issn=0167-7055&rft.eissn=1467-8659&rft.volume=40&rft.issue=5&rft.spage=157&rft.epage=167&rft_id=info:doi/10.1111%2Fcgf.14364&rft.externalDBID=10.1111%252Fcgf.14364&rft.externalDocID=CGF14364
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-7055&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-7055&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-7055&client=summon