Deep-Learning-Based 3-D Surface Reconstruction-A Survey
In the last decade, deep learning (DL) has significantly impacted industry and science. Initially largely motivated by computer vision tasks in 2-D imagery, the focus has shifted toward 3-D data analysis. In particular, 3-D surface reconstruction, i.e., reconstructing a 3-D shape from sparse input,...
Uložené v:
| Vydané v: | Proceedings of the IEEE Ročník 111; číslo 11; s. 1464 - 1501 |
|---|---|
| Hlavní autori: | , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
New York
IEEE
01.11.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Predmet: | |
| ISSN: | 0018-9219, 1558-2256 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | In the last decade, deep learning (DL) has significantly impacted industry and science. Initially largely motivated by computer vision tasks in 2-D imagery, the focus has shifted toward 3-D data analysis. In particular, 3-D surface reconstruction, i.e., reconstructing a 3-D shape from sparse input, is of great interest to a large variety of application fields. DL-based approaches show promising quantitative and qualitative surface reconstruction performance compared to traditional computer vision and geometric algorithms. This survey provides a comprehensive overview of these DL-based methods for 3-D surface reconstruction. To this end, we will first discuss input data modalities, such as volumetric data, point clouds, and RGB, single-view, multiview, and depth images, along with corresponding acquisition technologies and common benchmark datasets. For practical purposes, we also discuss evaluation metrics enabling us to judge the reconstructive performance of different methods. The main part of the document will introduce a methodological taxonomy ranging from point- and mesh-based techniques to volumetric and implicit neural approaches. Recent research trends, both methodological and for applications, are highlighted, pointing toward future developments. |
|---|---|
| AbstractList | In the last decade, deep learning (DL) has significantly impacted industry and science. Initially largely motivated by computer vision tasks in 2-D imagery, the focus has shifted toward 3-D data analysis. In particular, 3-D surface reconstruction, i.e., reconstructing a 3-D shape from sparse input, is of great interest to a large variety of application fields. DL-based approaches show promising quantitative and qualitative surface reconstruction performance compared to traditional computer vision and geometric algorithms. This survey provides a comprehensive overview of these DL-based methods for 3-D surface reconstruction. To this end, we will first discuss input data modalities, such as volumetric data, point clouds, and RGB, single-view, multiview, and depth images, along with corresponding acquisition technologies and common benchmark datasets. For practical purposes, we also discuss evaluation metrics enabling us to judge the reconstructive performance of different methods. The main part of the document will introduce a methodological taxonomy ranging from point- and mesh-based techniques to volumetric and implicit neural approaches. Recent research trends, both methodological and for applications, are highlighted, pointing toward future developments. |
| Author | Niesner, Matthias Gotz, Markus Streit, Achim Cavallaro, Gabriele Farshian, Anis Debus, Charlotte Benediktsson, Jon Atli |
| Author_xml | – sequence: 1 givenname: Anis orcidid: 0000-0002-9888-0653 surname: Farshian fullname: Farshian, Anis email: anis.farshian@kit.edu organization: Steinbuch Centre for Computing, Karlsruhe Institute of Technology, Karlsruhe, Germany – sequence: 2 givenname: Markus orcidid: 0000-0002-2233-1041 surname: Gotz fullname: Gotz, Markus email: markus.goetz@kit.edu organization: Steinbuch Centre for Computing, Karlsruhe Institute of Technology, Karlsruhe, Germany – sequence: 3 givenname: Gabriele orcidid: 0000-0002-3239-9904 surname: Cavallaro fullname: Cavallaro, Gabriele email: cavallaro@fz-juelich.de organization: Jülich Supercomputing Centre, Forschungszentrum Jülich, Jülich, Germany – sequence: 4 givenname: Charlotte orcidid: 0000-0002-7156-2022 surname: Debus fullname: Debus, Charlotte email: charlotte.debus@kit.edu organization: Steinbuch Centre for Computing, Karlsruhe Institute of Technology, Karlsruhe, Germany – sequence: 5 givenname: Matthias orcidid: 0000-0001-6093-5199 surname: Niesner fullname: Niesner, Matthias email: niessner@tum.de organization: Department of Informatics, Visual Computing Laboratory, Technical University of Munich, Munich, Germany – sequence: 6 givenname: Jon Atli orcidid: 0000-0003-0621-9647 surname: Benediktsson fullname: Benediktsson, Jon Atli email: benedikt@hi.is organization: Faculty of Electrical and Computer Engineering, University of Iceland, Reykjavik, Iceland – sequence: 7 givenname: Achim surname: Streit fullname: Streit, Achim email: achim.streit@kit.edu organization: Steinbuch Centre for Computing, Karlsruhe Institute of Technology, Karlsruhe, Germany |
| BookMark | eNp9kE1PAjEQhhuDiYD-AeOBxHOx7WyX9ojgZ0gwqOemdKdmCXax3TXh37srHowHT3OYeebN-wxIL1QBCTnnbMw501ePT6vlbCyYgDGA4BnAEelzKRUVQuY90meMK6oF1ydkkNKGMQYyhz6ZzBF3dIE2hjK80WubsBgBnY-em-itw9EKXRVSHRtXl1Wg027xiftTcuztNuHZzxyS19ubl9k9XSzvHmbTBXWQsZquEcDJXEpYZ74oMi8zyVwudI58zdAyDmC9LJSS0istRSEKroXPM595BQyG5PLwdxerjwZTbTZVE0MbaYTSAiYyb8sOiThcuVilFNGbXSzfbdwbzkwnyHwLMp0g8yOohdQfyJW17VrW0Zbb_9GLA1oi4q8saPtIDV9lGnMx |
| CODEN | IEEPAD |
| CitedBy_id | crossref_primary_10_1111_cgf_15181 crossref_primary_10_1109_ACCESS_2025_3561456 crossref_primary_10_1177_14727978251352146 crossref_primary_10_1109_TVCG_2025_3540669 crossref_primary_10_1016_j_ijmecsci_2024_109308 crossref_primary_10_1109_TVCG_2025_3591770 crossref_primary_10_1016_j_engappai_2025_110773 crossref_primary_10_1145_3731212 crossref_primary_10_1016_j_engappai_2025_110550 crossref_primary_10_1016_j_rineng_2025_104236 crossref_primary_10_1109_ACCESS_2025_3581974 crossref_primary_10_1016_j_media_2024_103305 crossref_primary_10_1016_j_neucom_2024_129112 crossref_primary_10_1109_TPAMI_2024_3510932 crossref_primary_10_1145_3687956 |
| Cites_doi | 10.1142/9789812831699_0007 10.1016/0146-664x(82)90104-6 10.1214/aoms/1177729694 10.1109/cvpr.2018.00030 10.1109/2945.817351 10.1109/cvprw50498.2020.00184 10.3390/su12156080 10.1109/cvpr.2019.00467 10.3390/rs8110936 10.1109/cvpr.2019.00983 10.1109/cvpr.2019.00611 10.1145/2487228.2487237 10.1007/978-3-031-20062-5_28 10.5194/isprs-archives-xlii-2-w15-1157-2019 10.1109/iccv.2019.00166 10.1109/cvpr42600.2020.00133 10.1109/mgrs.2019.2937630 10.1109/iccv48922.2021.01407 10.1007/978-3-319-24574-4_28 10.1109/iccvw.2011.6130382 10.1109/iccv48922.2021.01198 10.1109/tpami.2019.2954885 10.1111/cgf.12802 10.1109/tpami.2020.3005434 10.1109/cvpr46437.2021.00741 10.1109/cvpr46437.2021.00854 10.5194/isprs-archives-xli-b1-169-2016 10.1109/iccv.2007.4408983 10.1145/3072959.3073608 10.1109/iccv48922.2021.00582 10.1016/j.rse.2019.05.027 10.1145/3478513.3480496 10.1109/cvpr.2018.00268 10.3390/s19040810 10.1111/cgf.13753 10.1162/neco.1997.9.8.1735 10.1186/s40537-021-00556-1 10.1109/cvpr.2012.6248074 10.1109/cvpr42600.2020.00491 10.1007/978-3-030-66096-3_48 10.1007/978-3-030-01267-0_23 10.1109/iccv.2019.01006 10.1109/CVPR42600.2020.00186 10.1016/s0167-9457(96)00048-6 10.1109/cvpr42600.2020.01054 10.1007/978-3-030-58536-5_19 10.1145/2834892.2834894 10.1109/cvpr42600.2020.00016 10.1109/3dv.2017.00081 10.1109/cvpr42600.2020.00209 10.1109/cvpr46437.2021.01018 10.1109/cvpr42600.2020.00700 10.1007/978-3-030-01252-6_40 10.1145/37401.37422 10.1109/cvpr.2017.264 10.1109/cvpr.2018.00295 10.1109/iccv.2019.00113 10.1109/cvpr.2015.7298807 10.1109/cvpr.2017.261 10.1109/wacv.2014.6836101 10.1109/cvpr42600.2020.00292 10.1109/tpami.2023.3298850 10.3390/rs11060717 10.1023/a:1026543900054 10.1109/cvpr46437.2021.00455 10.3390/rs11111306 10.1007/978-3-030-58598-3_5 10.1109/cvpr.2019.00571 10.1109/iccv.2019.00988 10.1109/cvpr.2019.00459 10.1109/iccv.2019.00239 10.1007/978-3-030-20887-5_23 10.1109/iccv.2017.99 10.1109/cvpr.2018.00308 10.1109/iccv.2019.00463 10.1109/cvpr.2019.01037 10.1109/cvpr.2016.609 10.1109/cvpr.2019.00572 10.1109/iccv48922.2021.00580 10.1109/tgrs.2015.2421051 10.1109/iccv.2015.114 10.1146/annurev.earth.28.1.169 10.1016/j.neunet.2014.09.003 10.1561/2200000056 10.1007/978-3-030-58452-8_1 10.1109/cvpr46437.2021.00286 10.1109/cvpr.2018.00029 10.1109/cvpr.2017.693 10.1007/s41095-021-0229-5 10.1109/3dv.2017.00017 10.14358/pers.76.10.1123 10.1007/978-3-030-58452-8_2 10.1109/iccv.1998.710701 10.1109/cvpr52688.2022.00539 10.1007/978-3-319-46484-8_38 10.1109/cvpr.2019.00025 10.1007/978-3-319-46723-8_49 10.1145/237170.237269 10.1109/cvpr.2015.7298655 10.1109/cvpr46437.2021.00466 10.1109/iccv.2017.230 10.1016/0893-6080(89)90020-8 10.1016/j.measurement.2017.07.028 10.1109/cvpr42600.2020.00264 10.1145/3386569.3392415 10.1109/iccv.2013.458 10.1145/3197517.3201301 10.1145/3306346.3322959 10.1109/cvpr.2015.7298801 10.1109/iccv48922.2021.01386 10.1109/icmla51294.2020.00073 10.1109/cvpr.2019.00109 10.5194/isprsannals-i-3-293-2012 10.1109/icra40945.2020.9197503 10.1016/j.ophoto.2021.100001 10.1109/cvpr42600.2020.00356 10.1109/cvpr.2018.00209 10.1109/cvpr.2019.00352 10.1080/10298436.2016.1187730 10.1109/iccv48922.2021.00577 10.3390/rs11131540 10.1109/iccv.2019.00464 10.1109/cvpr.2006.19 10.1007/978-3-319-46466-4_29 10.1109/cvpr.2018.00411 10.1109/cvpr.2016.434 10.1109/cvpr.2019.00609 10.1007/978-3-030-58580-8_31 10.1111/cgf.13343 10.1145/3588432.3591516 10.1109/iccv.2019.00548 10.1109/tpds.2018.2829724 10.1111/cgf.13386 10.1007/s11831-019-09320-4 10.1007/978-3-030-01252-6_4 10.1145/3478513.3480487 10.1109/cvpr.2017.16 10.1117/12.148710 10.1109/iros.2015.7353481 10.1109/cvpr.2017.701 10.1109/access.2019.2939201 10.1109/cvpr.2019.00319 10.1111/1467-8659.00669 10.1109/cvpr.2016.586 10.1111/cgf.14340 10.1007/978-3-030-58526-6_36 10.1145/3528223.3530127 10.1007/978-3-030-58517-4_18 10.1109/iccv.2013.372 10.1201/9781420051438 10.1109/iccv.2019.00939 10.1007/978-3-030-58598-3_4 10.5194/isprs-annals-iv-1-w1-91-2017 10.1007/978-3-030-58452-8_24 10.1016/j.visinf.2021.10.003 10.1109/jstsp.2012.2208177 10.1109/ICCV51070.2023.01804 10.1109/cvpr46437.2021.00643 10.1109/iv47402.2020.9304812 10.1145/3272127.3275050 10.1109/iccv48922.2021.01245 10.1007/978-3-030-58580-8_22 10.1109/cvpr.2018.00207 10.1109/iccv.2017.322 10.1109/CVPR46437.2021.01120 10.1016/j.cviu.2015.05.006 10.1109/iccv48922.2021.01272 10.1109/cvpr.2018.00409 10.1109/cvpr42600.2020.00093 10.1109/cvpr.2018.00478 10.1109/CVPR.2014.59 10.1109/iccv48922.2021.01408 10.1007/978-3-030-58558-7_7 10.1145/133994.134011 10.1109/ICCV48922.2021.00554 10.1109/igarss.1999.772008 10.1109/cvpr.2019.00985 10.1088/1742-6596/1087/6/062031 10.1109/cvpr.2019.00100 10.1109/cvpr.2016.90 10.1038/nature14539 10.1109/cvpr42600.2020.00604 10.1109/3dv.2017.00054 10.1371/journal.pone.0220253 10.1177/0278364913491297 10.1016/0146-664x(80)90055-6 10.48550/arXiv.1312.6114 10.1109/iccv48922.2021.00581 10.1109/iccv.2017.292 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SP 8FD L7M |
| DOI | 10.1109/JPROC.2023.3321433 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace |
| DatabaseTitle | CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-2256 |
| EndPage | 1501 |
| ExternalDocumentID | 10_1109_JPROC_2023_3321433 10301359 |
| Genre | orig-research |
| GroupedDBID | -DZ -~X .DC 0R~ 123 1OL 29P 3EH 4.4 6IK 85S 97E 9M8 AAJGR AAWTH ABAZT ABFSI ABJNI ABQJQ ABVLG ACBEA ACGFS AENEX AETEA AETIX AFOGA AGNAY AGQYO AGSQL AHBIQ AIBXA ALLEH ALMA_UNASSIGNED_HOLDINGS AZLTO BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD ESBDL FA8 HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 MVM O9- OCL RIA RIE RIU RNS TAE TN5 TWZ UDY UHB UKR UQL VOH WHG XJT XOL YNT ZCA ZXP ZY4 ~02 AAYXX CITATION 7SP 8FD L7M |
| ID | FETCH-LOGICAL-c340t-be33c56553b4fdd4f5450c6296e1b0ea0133af5d8855f8952d2d192f64f4f8303 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 19 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001103912800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0018-9219 |
| IngestDate | Sun Nov 30 04:08:45 EST 2025 Tue Nov 18 21:25:26 EST 2025 Sat Nov 29 06:01:44 EST 2025 Wed Aug 27 02:24:42 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 11 |
| Language | English |
| License | https://creativecommons.org/licenses/by/4.0/legalcode |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c340t-be33c56553b4fdd4f5450c6296e1b0ea0133af5d8855f8952d2d192f64f4f8303 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-9888-0653 0000-0002-3239-9904 0000-0002-2233-1041 0000-0001-6093-5199 0000-0002-7156-2022 0000-0003-0621-9647 |
| OpenAccessLink | https://ieeexplore.ieee.org/document/10301359 |
| PQID | 2892375643 |
| PQPubID | 85453 |
| PageCount | 38 |
| ParticipantIDs | proquest_journals_2892375643 ieee_primary_10301359 crossref_primary_10_1109_JPROC_2023_3321433 crossref_citationtrail_10_1109_JPROC_2023_3321433 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-11-01 |
| PublicationDateYYYYMMDD | 2023-11-01 |
| PublicationDate_xml | – month: 11 year: 2023 text: 2023-11-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | Proceedings of the IEEE |
| PublicationTitleAbbrev | JPROC |
| PublicationYear | 2023 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref57 ref207 ref56 ref59 (ref115) 2014 ref58 ref206 ref52 ref55 ref209 ref210 ref211 ref50 Dhariwal (ref244); 34 ref46 ref218 ref45 ref219 ref48 ref47 ref217 ref42 ref41 ref215 ref44 ref212 ref43 Hu (ref114) ref213 ref49 Kato (ref123) 2020 ref7 ref9 ref4 ref3 ref6 Rezende (ref152) ref5 ref100 Kazhdan (ref130); 6 ref101 ref40 ref220 Yariv (ref226); 34 ref35 ref34 ref37 ref36 Choi (ref232) 2016 ref30 ref33 ref32 Silberman (ref104) 2012 ref39 ref38 ref24 ref26 ref25 Hegde (ref129) 2016 ref20 ref22 Wang (ref216) 2021 ref28 ref27 ref29 Thomas (ref205) 2018 ref200 ref128 ref97 ref126 ref99 ref124 ref245 ref98 ref125 ref246 Fuchs (ref204); 33 Sedaghat (ref127) 2016 ref93 ref133 ref92 ref134 ref95 ref131 ref94 ref132 ref91 ref90 ref89 ref139 ref86 ref85 ref138 ref88 ref135 ref87 Venkatesh (ref54) 2020 Kazhdan (ref8); 7 ref82 ref144 ref81 ref145 Van Oord (ref180) ref84 ref142 ref83 ref143 ref140 ref141 ref80 Chibane (ref53) 2020 ref79 ref229 ref78 ref109 ref106 ref107 ref228 ref75 ref74 ref105 ref77 ref102 ref223 ref76 ref103 Bozic (ref237); 33 Grathwohl (ref154) 2018 Bi (ref214) 2020 LeCun (ref240) 2021 ref71 ref111 ref70 ref73 ref230 ref72 ref110 ref231 ref68 ref119 ref67 ref117 ref69 ref118 ref239 ref64 ref236 ref63 ref66 ref234 ref65 Duggal (ref201) 2021 ref235 Xu (ref196) 2019 Smith (ref171) 2019 ref60 ref122 Chang (ref96) 2015 ref62 ref120 ref121 Vaswani (ref208) ref168 ref169 Yu et al (ref227) 2022 ref170 ref177 ref178 ref176 Gao (ref221) 2022 ref173 ref174 ref172 Wang (ref224); 35 Ho (ref242); 33 Sitzmann (ref193) 2019 Achlioptas (ref31); 80 ref181 Chen (ref153) 2018 ref188 ref189 ref186 ref187 ref184 Fu (ref113) 2020 ref185 ref182 You (ref179); 80 ref183 Sohl-Dickstein (ref241); 37 ref148 ref146 ref147 Radford (ref137) 2015 Fu (ref112) 2020 ref155 ref156 ref151 ref150 Fu (ref225); 35 ref159 ref157 ref158 ref166 ref167 Nichol (ref243) ref164 ref165 ref162 ref163 ref160 ref161 ref13 ref12 ref15 ref14 ref11 ref10 ref17 ref16 Zhao (ref238) ref19 ref18 Goodfellow (ref136) 2014 Turk (ref116) 2021 Sitzmann (ref51); 33 Wu (ref23) 2016 Brock (ref21) 2016 Goodfellow (ref2) 2016 Yariv (ref195); 33 Qi (ref149); 31 De Deuge (ref108); 2 Chatzipantazis (ref203) 2022 ref1 Liu (ref202) 2019 ref191 ref192 ref190 ref199 ref197 ref198 ref194 Zhang (ref61) 2020 Kar (ref175) 2017 (ref233) 2023 Wang (ref222); 34 |
| References_xml | – ident: ref12 doi: 10.1142/9789812831699_0007 – ident: ref142 doi: 10.1016/0146-664x(82)90104-6 – ident: ref121 doi: 10.1214/aoms/1177729694 – ident: ref34 doi: 10.1109/cvpr.2018.00030 – ident: ref10 doi: 10.1109/2945.817351 – ident: ref36 doi: 10.1109/cvprw50498.2020.00184 – ident: ref83 doi: 10.3390/su12156080 – volume-title: 3D Warehouse year: 2023 ident: ref233 – ident: ref71 doi: 10.1109/cvpr.2019.00467 – ident: ref75 doi: 10.3390/rs8110936 – ident: ref109 doi: 10.1109/cvpr.2019.00983 – ident: ref156 doi: 10.1109/cvpr.2019.00611 – volume: 33 start-page: 6840 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref242 article-title: Denoising diffusion probabilistic models – start-page: 8162 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref243 article-title: Improved denoising diffusion probabilistic models – ident: ref9 doi: 10.1145/2487228.2487237 – year: 2022 ident: ref203 article-title: SE(3)-equivariant attention networks for shape reconstruction in function space publication-title: arXiv:2204.02394 – ident: ref207 doi: 10.1007/978-3-031-20062-5_28 – ident: ref95 doi: 10.5194/isprs-archives-xlii-2-w15-1157-2019 – ident: ref161 doi: 10.1109/iccv.2019.00166 – ident: ref198 doi: 10.1109/cvpr42600.2020.00133 – ident: ref16 doi: 10.1109/mgrs.2019.2937630 – ident: ref60 doi: 10.1109/iccv48922.2021.01407 – ident: ref186 doi: 10.1007/978-3-319-24574-4_28 – ident: ref107 doi: 10.1109/iccvw.2011.6130382 – ident: ref206 doi: 10.1109/iccv48922.2021.01198 – year: 2020 ident: ref214 article-title: Neural reflectance fields for appearance acquisition publication-title: arXiv:2008.03824 – volume: 2 start-page: 1 volume-title: Proc. Australas. Conf. Robot. Autom. ident: ref108 article-title: Unsupervised feature learning for classification of outdoor 3D scans – start-page: 4975 volume-title: Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) ident: ref114 article-title: Towards semantic segmentation of urban-scale 3D point clouds: A dataset, benchmarks and challenges – ident: ref19 doi: 10.1109/tpami.2019.2954885 – ident: ref17 doi: 10.1111/cgf.12802 – ident: ref14 doi: 10.1109/tpami.2020.3005434 – ident: ref64 doi: 10.1109/cvpr46437.2021.00741 – ident: ref66 doi: 10.1109/cvpr46437.2021.00854 – ident: ref89 doi: 10.5194/isprs-archives-xli-b1-169-2016 – year: 2018 ident: ref154 article-title: FFJORD: Free-form continuous dynamics for scalable reversible generative models publication-title: arXiv:1810.01367 – year: 2020 ident: ref112 article-title: 3D-FRONT: 3D furnished rooms with layOuts and semaNTics publication-title: arXiv:2011.09127 – ident: ref145 doi: 10.1109/iccv.2007.4408983 – ident: ref147 doi: 10.1145/3072959.3073608 – year: 2018 ident: ref153 article-title: Neural ordinary differential equations publication-title: arXiv:1806.07366 – volume: 7 start-page: 61 volume-title: Proc. Eurographics Symp. Geometry Process. ident: ref8 article-title: Poisson surface reconstruction – volume: 33 start-page: 1403 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref237 article-title: TransformerFusion: Monocular RGB scene reconstruction using transformers – ident: ref220 doi: 10.1109/iccv48922.2021.00582 – ident: ref77 doi: 10.1016/j.rse.2019.05.027 – year: 2016 ident: ref129 article-title: FusionNet: 3D object classification using multiple data representations publication-title: arXiv:1607.05695 – ident: ref215 doi: 10.1145/3478513.3480496 – ident: ref168 doi: 10.1109/cvpr.2018.00268 – ident: ref13 doi: 10.3390/s19040810 – ident: ref170 doi: 10.1111/cgf.13753 – start-page: 1530 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref152 article-title: Variational inference with normalizing flows – ident: ref132 doi: 10.1162/neco.1997.9.8.1735 – ident: ref177 doi: 10.1186/s40537-021-00556-1 – volume: 34 start-page: 27171 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref222 article-title: NeuS: Learning neural implicit surfaces by volume rendering for multi-view reconstruction – volume: 33 start-page: 2492 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref195 article-title: Multiview neural surface reconstruction by disentangling geometry and appearance – ident: ref99 doi: 10.1109/cvpr.2012.6248074 – ident: ref184 doi: 10.1109/cvpr42600.2020.00491 – ident: ref185 doi: 10.1007/978-3-030-66096-3_48 – ident: ref40 doi: 10.1007/978-3-030-01267-0_23 – ident: ref70 doi: 10.1109/iccv.2019.01006 – volume: 35 start-page: 3403 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref225 article-title: Geo-Neus: Geometry-consistent neural implicit surfaces learning for multi-view reconstruction – ident: ref235 doi: 10.1109/CVPR42600.2020.00186 – ident: ref94 doi: 10.1016/s0167-9457(96)00048-6 – ident: ref169 doi: 10.1109/cvpr42600.2020.01054 – ident: ref189 doi: 10.1007/978-3-030-58536-5_19 – ident: ref6 doi: 10.1145/2834892.2834894 – year: 2015 ident: ref96 article-title: ShapeNet: An information-rich 3D model repository publication-title: arXiv:1512.03012 – ident: ref188 doi: 10.1109/cvpr42600.2020.00016 – ident: ref103 doi: 10.1109/3dv.2017.00081 – ident: ref197 doi: 10.1109/cvpr42600.2020.00209 – ident: ref217 doi: 10.1109/cvpr46437.2021.01018 – ident: ref56 doi: 10.1109/cvpr42600.2020.00700 – ident: ref138 doi: 10.1007/978-3-030-01252-6_40 – year: 2020 ident: ref123 article-title: Differentiable rendering: A survey publication-title: arXiv:2006.12057 – ident: ref125 doi: 10.1145/37401.37422 – ident: ref30 doi: 10.1109/cvpr.2017.264 – ident: ref155 doi: 10.1109/cvpr.2018.00295 – ident: ref39 doi: 10.1109/iccv.2019.00113 – ident: ref133 doi: 10.1109/cvpr.2015.7298807 – ident: ref102 doi: 10.1109/cvpr.2017.261 – start-page: 1747 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref180 article-title: Pixel recurrent neural networks – start-page: 746 volume-title: Eur. Conf. Comput. Vis. year: 2012 ident: ref104 article-title: Indoor segmentation and support inference from RGBD images – volume: 33 start-page: 7462 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref51 article-title: Implicit neural representations with periodic activation functions – ident: ref229 doi: 10.1109/wacv.2014.6836101 – ident: ref37 doi: 10.1109/cvpr42600.2020.00292 – ident: ref5 doi: 10.1109/tpami.2023.3298850 – ident: ref82 doi: 10.3390/rs11060717 – ident: ref118 doi: 10.1023/a:1026543900054 – ident: ref62 doi: 10.1109/cvpr46437.2021.00455 – ident: ref93 doi: 10.3390/rs11111306 – ident: ref35 doi: 10.1007/978-3-030-58598-3_5 – ident: ref162 doi: 10.1109/cvpr.2019.00571 – ident: ref44 doi: 10.1109/iccv.2019.00988 – ident: ref45 doi: 10.1109/cvpr.2019.00459 – ident: ref191 doi: 10.1109/iccv.2019.00239 – ident: ref172 doi: 10.1007/978-3-030-20887-5_23 – year: 2014 ident: ref115 publication-title: The Stanford Computer Graphics Laboratory – ident: ref150 doi: 10.1109/iccv.2017.99 – ident: ref42 doi: 10.1109/cvpr.2018.00308 – volume: 80 start-page: 40 volume-title: Proc. 35th Int. Conf. Mach. Learn. ident: ref31 article-title: Learning representations and generative models for 3D point clouds – volume: 31 start-page: 5099 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref149 article-title: PointNet++: Deep hierarchical feature learning on point sets in a metric space – ident: ref192 doi: 10.1109/iccv.2019.00463 – ident: ref174 doi: 10.1109/cvpr.2019.01037 – ident: ref128 doi: 10.1109/cvpr.2016.609 – ident: ref43 doi: 10.1109/cvpr.2019.00572 – volume: 6 start-page: 156 volume-title: Proc. Symp. Geometry Process. ident: ref130 article-title: Rotation invariant spherical harmonic representation of 3D shape descriptors – ident: ref210 doi: 10.1109/iccv48922.2021.00580 – ident: ref74 doi: 10.1109/tgrs.2015.2421051 – ident: ref131 doi: 10.1109/iccv.2015.114 – ident: ref91 doi: 10.1146/annurev.earth.28.1.169 – ident: ref3 doi: 10.1016/j.neunet.2014.09.003 – ident: ref135 doi: 10.1561/2200000056 – ident: ref165 doi: 10.1007/978-3-030-58452-8_1 – ident: ref245 doi: 10.1109/cvpr46437.2021.00286 – ident: ref32 doi: 10.1109/cvpr.2018.00029 – ident: ref24 doi: 10.1109/cvpr.2017.693 – ident: ref239 doi: 10.1007/s41095-021-0229-5 – ident: ref26 doi: 10.1109/3dv.2017.00017 – year: 2020 ident: ref61 article-title: NeRF++: Analyzing and improving neural radiance fields publication-title: arXiv:2010.07492 – ident: ref84 doi: 10.14358/pers.76.10.1123 – ident: ref159 doi: 10.1007/978-3-030-58452-8_2 – ident: ref117 doi: 10.1109/iccv.1998.710701 – ident: ref211 doi: 10.1109/cvpr52688.2022.00539 – volume: 80 start-page: 5708 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref179 article-title: GraphRNN: Generating realistic graphs with deep auto-regressive models – ident: ref20 doi: 10.1007/978-3-319-46484-8_38 – ident: ref50 doi: 10.1109/cvpr.2019.00025 – ident: ref187 doi: 10.1007/978-3-319-46723-8_49 – volume-title: SDFStudio: A Unified Framework for Surface Reconstruction year: 2022 ident: ref227 – ident: ref124 doi: 10.1145/237170.237269 – ident: ref106 doi: 10.1109/cvpr.2015.7298655 – start-page: 16239 volume-title: Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV) ident: ref238 article-title: Point transformer – ident: ref209 doi: 10.1109/cvpr46437.2021.00466 – ident: ref29 doi: 10.1109/iccv.2017.230 – ident: ref181 doi: 10.1016/0893-6080(89)90020-8 – ident: ref78 doi: 10.1016/j.measurement.2017.07.028 – ident: ref52 doi: 10.1109/cvpr42600.2020.00264 – ident: ref41 doi: 10.1145/3386569.3392415 – year: 2017 ident: ref175 article-title: Learning a multi-view stereo machine publication-title: arXiv:1708.05375 – year: 2016 ident: ref232 article-title: A large dataset of object scans publication-title: arXiv:1602.02481 – ident: ref105 doi: 10.1109/iccv.2013.458 – ident: ref160 doi: 10.1145/3197517.3201301 – ident: ref176 doi: 10.1145/3306346.3322959 – ident: ref98 doi: 10.1109/cvpr.2015.7298801 – ident: ref63 doi: 10.1109/iccv48922.2021.01386 – ident: ref120 doi: 10.1109/icmla51294.2020.00073 – ident: ref163 doi: 10.1109/cvpr.2019.00109 – ident: ref79 doi: 10.5194/isprsannals-i-3-293-2012 – ident: ref166 doi: 10.1109/icra40945.2020.9197503 – ident: ref111 doi: 10.1016/j.ophoto.2021.100001 – ident: ref194 doi: 10.1109/cvpr42600.2020.00356 – ident: ref25 doi: 10.1109/cvpr.2018.00209 – year: 2020 ident: ref54 article-title: DUDE: Deep unsigned distance embeddings for hi-fidelity representation of complex 3D surfaces publication-title: arXiv:2011.02570 – ident: ref119 doi: 10.1109/cvpr.2019.00352 – ident: ref87 doi: 10.1080/10298436.2016.1187730 – ident: ref246 doi: 10.1109/iccv48922.2021.00577 – ident: ref80 doi: 10.3390/rs11131540 – ident: ref33 doi: 10.1109/iccv.2019.00464 – ident: ref86 doi: 10.1109/cvpr.2006.19 – ident: ref22 doi: 10.1007/978-3-319-46466-4_29 – year: 2016 ident: ref21 article-title: Generative and discriminative voxel modeling with convolutional neural networks publication-title: arXiv:1608.04236 – ident: ref69 doi: 10.1109/cvpr.2018.00411 – ident: ref230 doi: 10.1109/cvpr.2016.434 – ident: ref49 doi: 10.1109/cvpr.2019.00609 – ident: ref46 doi: 10.1007/978-3-030-58580-8_31 – ident: ref158 doi: 10.1111/cgf.13343 – year: 2019 ident: ref202 article-title: Learning to infer implicit surfaces without 3D supervision publication-title: arXiv:1911.00767 – ident: ref228 doi: 10.1145/3588432.3591516 – ident: ref190 doi: 10.1109/iccv.2019.00548 – ident: ref7 doi: 10.1109/tpds.2018.2829724 – ident: ref18 doi: 10.1111/cgf.13386 – ident: ref72 doi: 10.1007/s11831-019-09320-4 – ident: ref38 doi: 10.1007/978-3-030-01252-6_4 – ident: ref219 doi: 10.1145/3478513.3480487 – volume: 35 start-page: 1966 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref224 article-title: HF-NeuS: Improved surface reconstruction using high-frequency details – ident: ref148 doi: 10.1109/cvpr.2017.16 – ident: ref11 doi: 10.1117/12.148710 – ident: ref126 doi: 10.1109/iros.2015.7353481 – year: 2016 ident: ref127 article-title: Orientation-boosted voxel nets for 3D object recognition publication-title: arXiv:1604.03351 – ident: ref144 doi: 10.1109/cvpr.2017.701 – ident: ref15 doi: 10.1109/access.2019.2939201 – ident: ref140 doi: 10.1109/cvpr.2019.00319 – ident: ref122 doi: 10.1111/1467-8659.00669 – ident: ref146 doi: 10.1109/cvpr.2016.586 – ident: ref59 doi: 10.1111/cgf.14340 – volume-title: Self-Supervised Learning: The Dark Matter of Intelligence year: 2021 ident: ref240 – year: 2014 ident: ref136 article-title: Generative adversarial networks publication-title: arXiv:1406.2661 – ident: ref47 doi: 10.1007/978-3-030-58526-6_36 – ident: ref213 doi: 10.1145/3528223.3530127 – year: 2019 ident: ref171 article-title: GEOMetrics: Exploiting geometric structure for graph-encoded objects publication-title: arXiv:1901.11461 – volume: 33 start-page: 1970 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref204 article-title: SE(3)-transformers: 3D roto-translation equivariant attention networks – ident: ref183 doi: 10.1007/978-3-030-58517-4_18 – ident: ref231 doi: 10.1109/iccv.2013.372 – ident: ref73 doi: 10.1201/9781420051438 – ident: ref101 doi: 10.1109/iccv.2019.00939 – year: 2019 ident: ref193 article-title: Scene representation networks: Continuous 3D-Structure-Aware neural scene representations publication-title: arXiv:1906.01618 – ident: ref199 doi: 10.1007/978-3-030-58598-3_4 – ident: ref110 doi: 10.5194/isprs-annals-iv-1-w1-91-2017 – year: 2020 ident: ref113 article-title: 3D-FUTURE: 3D furniture shape with TextURE publication-title: arXiv:2009.09633 – ident: ref57 doi: 10.1007/978-3-030-58452-8_24 – ident: ref4 doi: 10.1016/j.visinf.2021.10.003 – year: 2020 ident: ref53 article-title: Neural unsigned distance fields for implicit function learning publication-title: arXiv:2010.13938 – ident: ref76 doi: 10.1109/jstsp.2012.2208177 – ident: ref212 doi: 10.1109/ICCV51070.2023.01804 – year: 2022 ident: ref221 article-title: NeRF: Neural radiance field in 3D vision, a comprehensive review publication-title: arXiv:2210.00379 – ident: ref218 doi: 10.1109/cvpr46437.2021.00643 – ident: ref81 doi: 10.1109/iv47402.2020.9304812 – ident: ref27 doi: 10.1145/3272127.3275050 – ident: ref65 doi: 10.1109/iccv48922.2021.01245 – ident: ref157 doi: 10.1007/978-3-030-58580-8_22 – ident: ref141 doi: 10.1109/cvpr.2018.00207 – ident: ref178 doi: 10.1109/iccv.2017.322 – ident: ref200 doi: 10.1109/CVPR46437.2021.01120 – ident: ref90 doi: 10.1016/j.cviu.2015.05.006 – ident: ref68 doi: 10.1109/iccv48922.2021.01272 – volume: 37 start-page: 2256 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref241 article-title: Deep unsupervised learning using nonequilibrium thermodynamics – volume-title: Large Geometric Models Archive year: 2021 ident: ref116 – year: 2015 ident: ref137 article-title: Unsupervised representation learning with deep convolutional generative adversarial networks publication-title: arXiv:1511.06434 – ident: ref167 doi: 10.1109/cvpr.2018.00409 – ident: ref139 doi: 10.1109/cvpr42600.2020.00093 – ident: ref151 doi: 10.1109/cvpr.2018.00478 – year: 2018 ident: ref205 article-title: Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds publication-title: arXiv:1802.08219 – start-page: 5998 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref208 article-title: Attention is all you need – ident: ref234 doi: 10.1109/CVPR.2014.59 – ident: ref58 doi: 10.1109/iccv48922.2021.01408 – ident: ref48 doi: 10.1007/978-3-030-58558-7_7 – ident: ref182 doi: 10.1145/133994.134011 – volume: 34 start-page: 8780 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref244 article-title: Diffusion models beat GANs on image synthesis – ident: ref223 doi: 10.1109/ICCV48922.2021.00554 – year: 2016 ident: ref23 article-title: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling publication-title: arXiv:1610.07584 – year: 2021 ident: ref216 article-title: NeRF–: Neural radiance fields without known camera parameters publication-title: arXiv:2102.07064 – ident: ref92 doi: 10.1109/igarss.1999.772008 – ident: ref164 doi: 10.1109/cvpr.2019.00985 – ident: ref85 doi: 10.1088/1742-6596/1087/6/062031 – ident: ref97 doi: 10.1109/cvpr.2019.00100 – ident: ref173 doi: 10.1109/cvpr.2016.90 – year: 2021 ident: ref201 article-title: Mending neural implicit modeling for 3D vehicle reconstruction in the wild publication-title: arXiv:2101.06860 – ident: ref1 doi: 10.1038/nature14539 – ident: ref55 doi: 10.1109/cvpr42600.2020.00604 – ident: ref28 doi: 10.1109/3dv.2017.00054 – ident: ref88 doi: 10.1371/journal.pone.0220253 – ident: ref100 doi: 10.1177/0278364913491297 – volume: 34 start-page: 4805 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref226 article-title: Volume rendering of neural implicit surfaces – ident: ref143 doi: 10.1016/0146-664x(80)90055-6 – year: 2019 ident: ref196 article-title: DISN: Deep implicit surface network for high-quality single-view 3D reconstruction publication-title: arXiv:1905.10711 – ident: ref134 doi: 10.48550/arXiv.1312.6114 – ident: ref67 doi: 10.1109/iccv48922.2021.00581 – volume-title: Deep Learning year: 2016 ident: ref2 – ident: ref236 doi: 10.1109/iccv.2017.292 |
| SSID | ssj0003563 |
| Score | 2.57522 |
| Snippet | In the last decade, deep learning (DL) has significantly impacted industry and science. Initially largely motivated by computer vision tasks in 2-D imagery,... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1464 |
| SubjectTerms | 3-D deep learning (DL) 3-D surface reconstruction Computer vision Data analysis Deep learning Geometric algorithms geometric DL Geometric modeling geometry processing Image acquisition Image reconstruction Laser radar Machine learning Point cloud compression Surface emitting lasers Surface reconstruction Surveys Taxonomy Three-dimensional displays |
| Title | Deep-Learning-Based 3-D Surface Reconstruction-A Survey |
| URI | https://ieeexplore.ieee.org/document/10301359 https://www.proquest.com/docview/2892375643 |
| Volume | 111 |
| WOSCitedRecordID | wos001103912800001&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-2256 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0003563 issn: 0018-9219 databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwGA1u-KAPXidOp_TBN8nWNknTPM7NISJzeIG9lTb5IoJsYzfw35ukmU5EwbdCkxJO-t2afucgdEFN1IdQm9pEUY4pBesHdYy1oGmc61DRwlHm3_F-Px0OxcA3q7teGABwP59B0166s3w1lgv7qaxlJbEiwkQFVTjnZbPWp9slzMumRcaCjR2uOmRC0bodPNx3mlYovEmsMA8h36KQk1X54YtdgOnt_nNpe2jHZ5JBu9z6fbQBowO0vcYveIh4F2CCPYXqC74yEUsFBHeDx8VU5xICW3x-Ucjitr2xhPcaeu5dP3VusFdKwJLQcI4LIESa1IyRgmqlqDZ5USiTWCQQFSHkZmkk10ylKWM6FSxWsTKpnU6opjo1UewIVUfjERyjoGBggCQUBJOUKp4XjIHSNI5UmAjI6yhaIZdJTyNu1SzeMldOhCJzaGcW7cyjXUeXn3MmJYnGn6NrFt-1kSW0ddRY7VDmDW2WmXoxJpyZvOrkl2mnaMs-vewfbKCqwRTO0KZczl9n03P3Dn0AHTvASg |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD7oFNQHrxOnU_vgm2Rrm6RtHudUvMwpXmBvpU1ORJBNtin4703STiei4FuhCQ1fem5Nz_cBHDAT9dHXpjZRLCaMofWDOiRasCTMtK9Y7ijzO3G3m_R64qZsVne9MIjofj7Dhr10Z_lqIF_tp7KmlcQKKBezMMcZC4OiXevT8VJeCqcFxoaNJU56ZHzRvLi5vW43rFR4g1ppHkq_xSEnrPLDG7sQc7ryz8WtwnKZS3qtYvPXYAb767A0xTC4AfEx4gspSVQfyZGJWcqj5Ni7ex3qTKJny88vElnSsjfe8L0KD6cn9-0zUmolEEmZPyY5UipNcsZpzrRSTJvMyJdRKCIMch8zszSaaa6ShHOdCB6qUJnkTkdMM52YOLYJlf6gj1vg5RwNkJSh4JIxFWc556i0wVv5kcCsBsEEuVSWROJWz-I5dQWFL1KHdmrRTku0a3D4OeeloNH4c3TV4js1soC2BvXJDqWlqY1SUzGGNOYms9r-Zdo-LJzdX3XSznn3cgcW7ZOKbsI6VAy-uAvz8m38NBruuffpA03zw5E |
| 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=Deep-Learning-Based+3-D+Surface+Reconstruction-A+Survey&rft.jtitle=Proceedings+of+the+IEEE&rft.au=Farshian%2C+Anis&rft.au=Gotz%2C+Markus&rft.au=Cavallaro%2C+Gabriele&rft.au=Debus%2C+Charlotte&rft.date=2023-11-01&rft.pub=IEEE&rft.issn=0018-9219&rft.volume=111&rft.issue=11&rft.spage=1464&rft.epage=1501&rft_id=info:doi/10.1109%2FJPROC.2023.3321433&rft.externalDocID=10301359 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9219&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9219&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9219&client=summon |