Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis
Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications of 3D computer vision. The progress of deep learning (DL) has impressively improved the capability and robustness of point cloud completion. However, the qu...
Saved in:
| Published in | IEEE transactions on intelligent transportation systems Vol. 23; no. 12; pp. 22862 - 22883 |
|---|---|
| Main Authors | , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
IEEE
01.12.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications of 3D computer vision. The progress of deep learning (DL) has impressively improved the capability and robustness of point cloud completion. However, the quality of completed point clouds is still needed to be further enhanced to meet the practical utilization. Therefore, this work aims to conduct a comprehensive survey on various methods, including point-based, view-based, convolution-based, graph-based, generative model-based, transformer-based approaches, etc. And this survey summarizes the comparisons among these methods to provoke further research insights. Besides, this review sums up the commonly used datasets and illustrates the applications of point cloud completion. Eventually, we also discussed possible research trends in this promptly expanding field. |
|---|---|
| AbstractList | Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications of 3D computer vision. The progress of deep learning (DL) has impressively improved the capability and robustness of point cloud completion. However, the quality of completed point clouds is still needed to be further enhanced to meet the practical utilization. Therefore, this work aims to conduct a comprehensive survey on various methods, including point-based, view-based, convolution-based, graph-based, generative model-based, transformer-based approaches, etc. And this survey summarizes the comparisons among these methods to provoke further research insights. Besides, this review sums up the commonly used datasets and illustrates the applications of point cloud completion. Eventually, we also discussed possible research trends in this promptly expanding field. |
| Author | Li, Zhijun Li, Yikang Hu, Xing Chen, Wen-Ming Ma, Tao Fei, Ben Yang, Weidong Ma, Lipeng |
| Author_xml | – sequence: 1 givenname: Ben orcidid: 0000-0002-3219-9996 surname: Fei fullname: Fei, Ben email: bfei21@m.fudan.edu.cn organization: Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China – sequence: 2 givenname: Weidong surname: Yang fullname: Yang, Weidong email: wdyang@fudan.edu.cn organization: Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China – sequence: 3 givenname: Wen-Ming orcidid: 0000-0003-0409-5118 surname: Chen fullname: Chen, Wen-Ming email: chenwm@fudan.edu.cn organization: Academy for Engineering and Technology, Fudan University, Shanghai, China – sequence: 4 givenname: Zhijun orcidid: 0000-0002-3909-488X surname: Li fullname: Li, Zhijun email: zjli@ieee.org organization: Department of Automation, University of Science and Technology of China, Hefei, China – sequence: 5 givenname: Yikang surname: Li fullname: Li, Yikang email: liyikang@pjlab.org.cn organization: Shanghai AI Laboratory, Shanghai, China – sequence: 6 givenname: Tao surname: Ma fullname: Ma, Tao email: matao@pjlab.org.cn organization: Shanghai AI Laboratory, Shanghai, China – sequence: 7 givenname: Xing surname: Hu fullname: Hu, Xing email: huxing@usst.edu.cn organization: School of Optical-Electrical Information and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, China – sequence: 8 givenname: Lipeng surname: Ma fullname: Ma, Lipeng email: lpma21@m.fudan.edu.cn organization: Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China |
| BookMark | eNp9kE9LwzAYh4NMcE4_gHgJeO5M2qZpjrPzz2Dg0HmUkiVvNaNLatJN9u1t2fDgwVwS3jzPy4_fORpYZwGhK0rGlBJxu5wtX8cxieNxQgXrzgkaUsbyiBCaDfp3nEaCMHKGzkNYd9OUUTpE74XbNB4-wQazA_wCOwPf2FV4CtDgOUhvjf2I7mQAjZMpXjhjW1zUbqtxr9bQGmfxwjsFIXQollbjiZX1PphwgU4rWQe4PN4j9PZwvyyeovnz46yYzCMVi6SN-IpIkgvBcq4rUqmYap2QXOci0UpBzCqpUp6mucoVrQhU2SrTZKW7b8oEl8kI3Rz2Nt59bSG05dptfRcilDFPeUY7THQUP1DKuxA8VKUyrezzt16auqSk7Lss-y7Lvsvy2GVn0j9m481G-v2_zvXBMQDwy4uc8YyT5Aec-oHM |
| CODEN | ITISFG |
| CitedBy_id | crossref_primary_10_1016_j_patcog_2024_110532 crossref_primary_10_1016_j_measurement_2024_116487 crossref_primary_10_1109_ACCESS_2024_3461828 crossref_primary_10_1016_j_measurement_2024_116246 crossref_primary_10_1016_j_isprsjprs_2023_09_008 crossref_primary_10_1111_cgf_15222 crossref_primary_10_1088_1361_6501_ad8fc2 crossref_primary_10_1109_ACCESS_2025_3547942 crossref_primary_10_1016_j_autcon_2023_105108 crossref_primary_10_1016_j_engappai_2023_107656 crossref_primary_10_3390_f16030513 crossref_primary_10_3390_sym16121680 crossref_primary_10_1016_j_oceaneng_2024_119112 crossref_primary_10_3390_app14020862 crossref_primary_10_1109_TVCG_2023_3344935 crossref_primary_10_1016_j_displa_2023_102456 crossref_primary_10_1016_j_neucom_2024_129037 crossref_primary_10_1016_j_neucom_2024_129313 crossref_primary_10_1016_j_ultras_2024_107381 crossref_primary_10_1109_TIP_2024_3512356 crossref_primary_10_1115_1_4056566 crossref_primary_10_1016_j_cag_2024_103915 crossref_primary_10_1016_j_ijrmms_2024_106005 crossref_primary_10_1111_cgf_15231 crossref_primary_10_1109_TIV_2024_3383108 crossref_primary_10_1109_TMM_2023_3318327 crossref_primary_10_1002_widm_1554 crossref_primary_10_1109_TRO_2025_3531816 crossref_primary_10_1007_s00371_024_03509_w crossref_primary_10_3390_automation5040028 crossref_primary_10_3390_e26030235 crossref_primary_10_1109_TITS_2024_3388276 crossref_primary_10_1016_j_eswa_2023_122419 crossref_primary_10_3390_jmse11071339 crossref_primary_10_1016_j_patter_2024_101147 crossref_primary_10_1111_2041_210X_14412 crossref_primary_10_1007_s41315_023_00303_0 crossref_primary_10_1016_j_knosys_2024_112453 crossref_primary_10_1109_ACCESS_2024_3411029 crossref_primary_10_1007_s00521_024_10659_4 crossref_primary_10_1109_ACCESS_2023_3266340 crossref_primary_10_1080_15230406_2024_2320150 crossref_primary_10_3390_rs16203763 crossref_primary_10_1016_j_cad_2025_103848 crossref_primary_10_3390_e25071018 crossref_primary_10_1109_TMM_2024_3521854 crossref_primary_10_1109_JSTARS_2024_3478069 crossref_primary_10_1186_s13640_024_00659_8 crossref_primary_10_1016_j_compag_2024_109673 crossref_primary_10_1109_ACCESS_2025_3528245 crossref_primary_10_1109_TGRS_2025_3545783 crossref_primary_10_1038_s41598_024_68084_5 crossref_primary_10_1016_j_gmod_2024_101233 crossref_primary_10_3390_rs15174338 crossref_primary_10_1007_s40747_023_01325_8 crossref_primary_10_1016_j_jmb_2024_168543 crossref_primary_10_1016_j_isprsjprs_2024_07_009 crossref_primary_10_1007_s00371_023_03237_7 crossref_primary_10_1080_19424280_2024_2319796 crossref_primary_10_1016_j_inffus_2024_102388 crossref_primary_10_3390_agriculture13102026 crossref_primary_10_1109_ACCESS_2025_3536004 crossref_primary_10_1016_j_media_2024_103439 crossref_primary_10_1016_j_compbiomed_2023_107519 crossref_primary_10_3390_en17205177 crossref_primary_10_1007_s11263_023_01820_y crossref_primary_10_1016_j_neucom_2025_129768 crossref_primary_10_1016_j_aej_2024_10_037 crossref_primary_10_1109_ACCESS_2023_3339657 crossref_primary_10_1186_s13007_025_01347_y crossref_primary_10_1007_s00521_024_09624_y crossref_primary_10_1109_TITS_2023_3344806 crossref_primary_10_2298_CSIS230725043Z crossref_primary_10_3390_rs14153617 crossref_primary_10_1016_j_compag_2023_108512 crossref_primary_10_1109_LRA_2024_3483037 crossref_primary_10_1109_TVCG_2023_3236061 crossref_primary_10_3390_app14041510 |
| Cites_doi | 10.1109/CVPR52688.2022.00162 10.1109/CVPR46437.2021.00181 10.1109/CVPR46437.2021.01151 10.1007/978-3-030-61401-0_28 10.1109/IROS45743.2020.9340862 10.1609/aaai.v34i07.6734 10.1007/s41095-021-0229-5 10.1109/CVPR.2017.16 10.1109/CVPR.2019.00605 10.1109/MFI.2016.7849532 10.1109/CVPR.2019.00047 10.1109/CVPR46437.2021.01511 10.1007/978-3-030-89370-5_30 10.1109/CVPR.2017.693 10.1016/j.neucom.2021.07.035 10.1109/WACV.2019.00122 10.1007/978-3-319-49409-8_20 10.1243/PIME_PROC_1994_208_056_02 10.1109/WACV.2019.00117 10.1109/LRA.2022.3146585 10.1109/IROS51168.2021.9636483 10.1016/S0890-6955(02)00030-5 10.1145/3326362 10.1007/978-3-030-58595-2_31 10.1145/3474085.3475348 10.1016/j.neucom.2021.07.087 10.1109/ICCV48922.2021.01227 10.1109/TMM.2020.2976627 10.24963/ijcai.2019/517 10.1109/ICCV48922.2021.01294 10.1109/CVPR.2019.00352 10.1109/CVPR42600.2020.00087 10.1109/WACV45572.2020.9093430 10.1109/ICCV.2017.252 10.1609/aaai.v34i07.6827 10.1109/ICCV.2019.00825 10.1609/aaai.v35i4.16478 10.1007/978-3-030-01270-0_39 10.1109/CVPR52688.2022.00546 10.1109/ICIP42928.2021.9506234 10.1145/3436369.3437421 10.1109/ICCV.2017.19 10.1177/0278364913491297 10.1109/ICCV.2019.00651 10.1109/ICCV48922.2021.01226 10.1109/ICCV48922.2021.01228 10.1109/ICCV.2019.00730 10.1145/3394171.3413648 10.1109/CVPR.2019.00985 10.1109/CVPR46437.2021.00736 10.1109/LRA.2020.2994483 10.1007/978-3-030-58558-7_17 10.1109/JETCAS.2018.2885981 10.1109/TPAMI.2020.3005434 10.3390/ijgi10070482 10.1109/CVPR42600.2020.00700 10.1109/3DV50981.2020.00021 10.1109/CCDC.2019.8832956 10.1016/j.neucom.2019.12.032 10.1109/CVPR42600.2020.00201 10.1061/(ASCE)CP.1943-5487.0000028 10.1109/CVPR52688.2022.00040 10.1109/CVPR46437.2021.01013 10.1109/CVPR.2019.00910 10.1117/12.2586422 10.1007/978-3-030-58580-8_5 10.1109/CVPR52688.2022.00177 10.1109/MCG.2021.3065533 10.1109/CVPR46437.2021.01268 10.1109/CVPR.2018.00295 10.1109/ICCV48922.2021.01595 10.1109/LRA.2021.3097081 10.1109/CVPR46437.2021.01563 10.1109/TGRS.2021.3105551 10.1109/ICCVW.2019.00506 10.1109/3DV.2018.00088 10.1109/CVPR.2017.264 10.1016/j.cagd.2020.101925 10.1109/ACCESS.2020.2973003 10.1016/j.imavis.2021.104193 10.1016/j.neucom.2021.06.080 10.5194/isprs-annals-V-2-2020-933-2020 10.1109/CVPR.2018.00478 10.1109/ICCV48922.2021.00545 10.1109/ICPR48806.2021.9413104 10.1016/j.tust.2010.04.008 10.1109/CVPR46437.2021.00842 10.1109/ICCV48922.2021.00964 10.1109/CVPR46437.2021.00738 10.1007/978-3-030-60633-6_27 10.1109/LRA.2020.3048658 10.1109/CVPR42600.2020.00768 10.1109/CVPR.2018.00029 10.1109/CVPR46437.2021.01288 10.1109/CVPR.2019.00110 10.1109/CVPR46437.2021.00459 10.1109/CVPR.2018.00109 10.1109/TIP.2021.3073318 10.1109/CVPR.2018.00209 10.1007/s11831-019-09320-4 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD FR3 JQ2 KR7 L7M L~C L~D |
| DOI | 10.1109/TITS.2022.3195555 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Civil Engineering Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Civil Engineering Abstracts |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-0016 |
| EndPage | 22883 |
| ExternalDocumentID | 10_1109_TITS_2022_3195555 9857670 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Natural Science Foundation of China grantid: U2033029 funderid: 10.13039/501100001809 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS ZY4 AAYXX CITATION RIG 7SC 7SP 8FD FR3 JQ2 KR7 L7M L~C L~D |
| ID | FETCH-LOGICAL-c293t-7b0a0899587df0fc21dd308d893dcce25fac47448c8c1f0ef6b6d0bd93d1597a3 |
| IEDL.DBID | RIE |
| ISSN | 1524-9050 |
| IngestDate | Sun Jun 29 12:34:14 EDT 2025 Tue Jul 01 04:29:10 EDT 2025 Thu Apr 24 23:11:23 EDT 2025 Wed Aug 27 02:15:00 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 12 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c293t-7b0a0899587df0fc21dd308d893dcce25fac47448c8c1f0ef6b6d0bd93d1597a3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-3219-9996 0000-0002-3909-488X 0000-0003-0409-5118 |
| PQID | 2747611599 |
| PQPubID | 75735 |
| PageCount | 22 |
| ParticipantIDs | ieee_primary_9857670 proquest_journals_2747611599 crossref_citationtrail_10_1109_TITS_2022_3195555 crossref_primary_10_1109_TITS_2022_3195555 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2022-12-01 |
| PublicationDateYYYYMMDD | 2022-12-01 |
| PublicationDate_xml | – month: 12 year: 2022 text: 2022-12-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on intelligent transportation systems |
| PublicationTitleAbbrev | TITS |
| PublicationYear | 2022 |
| 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 | ref56 ref59 ref52 ref55 fröhlich (ref129) 2004; 36 li (ref101) 2018 ref54 lyu (ref37) 2021 zhang (ref10) 2022 cheng (ref136) 2020 achlioptas (ref93) 2018 ref51 ref50 ref45 zhang (ref90) 2020 qi (ref19) 2017 wu (ref35) 2015 ref48 ref47 ref42 ref41 ref44 ref43 fan (ref5) 2022 ref49 ref8 ref9 ref4 spurek (ref114) 2021 ref40 yan (ref137) 2020 ref34 ref36 wang (ref106) 2020 ref31 zhao (ref57) 2021 ref30 ref33 ref38 huang (ref1) 2021 ref24 ref23 ref26 ref25 wu (ref39) 2021 ref22 liu (ref17) 2019 dosovitskiy (ref119) 2020 ref27 ref29 zhang (ref81) 2019 wen (ref21) 2022 chen (ref98) 2019 ref13 ref12 ref128 ref15 su (ref6) 2022 ref14 ref126 ref97 ref127 ref96 ref124 ref99 ref11 ma (ref7) 2022 ref16 ref18 egiazarian (ref100) 2019 groueix (ref20) 2018 ref133 ref134 ref92 ref131 ref95 xie (ref75) 2020 ref132 ref94 ref130 son (ref125) 2020 ref89 ref139 ref86 ref138 ref85 ref135 ref88 ref87 li (ref58) 2021 vaswani (ref118) 2017 ref82 ref84 ref83 ref80 ref79 ref78 li (ref69) 2018; 31 ref109 ref107 ref104 ref74 ref105 ref77 ref102 ref76 ref103 ref2 valsesia (ref108) 2018 nie (ref46) 2020 ref71 ref111 ref70 ref112 lu (ref3) 2020 ref73 ref72 ref110 wang (ref28) 2020 wang (ref63) 2022 ref68 parmar (ref120) 2018 ref67 ref117 ref64 ref115 ref116 ref66 ref113 ref65 ref60 ref122 ref123 ref62 goodfellow (ref91) 2014; 27 ref61 ref121 chang (ref32) 2015 mendoza (ref53) 2020 |
| References_xml | – ident: ref8 doi: 10.1109/CVPR52688.2022.00162 – ident: ref99 doi: 10.1109/CVPR46437.2021.00181 – start-page: 40 year: 2018 ident: ref93 article-title: Learning representations and generative models for 3D point clouds publication-title: Proc Int Conf Mach Learn – ident: ref84 doi: 10.1109/CVPR46437.2021.01151 – ident: ref115 doi: 10.1007/978-3-030-61401-0_28 – start-page: 216 year: 2018 ident: ref20 article-title: A papier-mâché approach to learning 3D surface generation publication-title: Proc IEEE Conf Comput Vis and Pattern Recog – ident: ref105 doi: 10.1109/IROS45743.2020.9340862 – start-page: 5998 year: 2017 ident: ref118 article-title: Attention is all you need publication-title: Proc Adv Neural Inf Process Syst – start-page: 4055 year: 2018 ident: ref120 article-title: Image transformer publication-title: Proc Int Conf Mach Learn – year: 2021 ident: ref39 article-title: Density-aware chamfer distance as a comprehensive metric for point cloud completion publication-title: arXiv 2111 12702 – ident: ref66 doi: 10.1609/aaai.v34i07.6734 – ident: ref121 doi: 10.1007/s41095-021-0229-5 – ident: ref18 doi: 10.1109/CVPR.2017.16 – year: 2019 ident: ref17 article-title: Point-voxel CNN for efficient 3D deep learning publication-title: arXiv 1907 03739 – ident: ref23 doi: 10.1109/CVPR.2019.00605 – ident: ref134 doi: 10.1109/MFI.2016.7849532 – ident: ref24 doi: 10.1109/CVPR.2019.00047 – ident: ref74 doi: 10.1109/CVPR46437.2021.01511 – year: 2015 ident: ref32 article-title: ShapeNet: An information-rich 3D model repository publication-title: arXiv 1512 03012 – ident: ref77 doi: 10.1007/978-3-030-89370-5_30 – ident: ref12 doi: 10.1109/CVPR.2017.693 – ident: ref86 doi: 10.1016/j.neucom.2021.07.035 – ident: ref94 doi: 10.1109/WACV.2019.00122 – year: 2020 ident: ref119 article-title: An image is worth 16×16 words: Transformers for image recognition at scale publication-title: arXiv 2010 11929 – ident: ref14 doi: 10.1007/978-3-319-49409-8_20 – year: 2019 ident: ref81 article-title: Linked dynamic graph CNN: Learning on point cloud via linking hierarchical features publication-title: arXiv 1904 10014 – ident: ref127 doi: 10.1243/PIME_PROC_1994_208_056_02 – start-page: 1912 year: 2015 ident: ref35 article-title: 3D ShapeNets: A deep representation for volumetric shapes publication-title: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR) – ident: ref22 doi: 10.1109/WACV.2019.00117 – ident: ref26 doi: 10.1109/LRA.2022.3146585 – ident: ref124 doi: 10.1109/IROS51168.2021.9636483 – volume: 31 start-page: 820 year: 2018 ident: ref69 article-title: PointCNN: Convolution on X-transformed points publication-title: Proc Adv Neural Inf Process Syst – ident: ref128 doi: 10.1016/S0890-6955(02)00030-5 – ident: ref80 doi: 10.1145/3326362 – ident: ref56 doi: 10.1007/978-3-030-58595-2_31 – ident: ref52 doi: 10.1145/3474085.3475348 – ident: ref96 doi: 10.1016/j.neucom.2021.07.087 – ident: ref33 doi: 10.1109/ICCV48922.2021.01227 – ident: ref109 doi: 10.1109/TMM.2020.2976627 – ident: ref83 doi: 10.24963/ijcai.2019/517 – ident: ref76 doi: 10.1109/ICCV48922.2021.01294 – ident: ref40 doi: 10.1109/CVPR.2019.00352 – ident: ref42 doi: 10.1109/CVPR42600.2020.00087 – ident: ref62 doi: 10.1109/WACV45572.2020.9093430 – ident: ref92 doi: 10.1109/ICCV.2017.252 – ident: ref31 doi: 10.1609/aaai.v34i07.6827 – ident: ref82 doi: 10.1109/ICCV.2019.00825 – ident: ref11 doi: 10.1609/aaai.v35i4.16478 – ident: ref139 doi: 10.1007/978-3-030-01270-0_39 – ident: ref4 doi: 10.1109/CVPR52688.2022.00546 – year: 2022 ident: ref7 article-title: Completing partial point clouds with outliers by collaborative completion and segmentation publication-title: arXiv 2203 09772 – year: 2019 ident: ref98 article-title: Unpaired point cloud completion on real scans using adversarial training publication-title: arXiv 1904 00069 – year: 2019 ident: ref100 article-title: Latent-space Laplacian pyramids for adversarial representation learning with 3D point clouds publication-title: arXiv 1912 06466 – ident: ref79 doi: 10.1109/ICIP42928.2021.9506234 – ident: ref61 doi: 10.1145/3436369.3437421 – ident: ref13 doi: 10.1109/ICCV.2017.19 – ident: ref34 doi: 10.1177/0278364913491297 – start-page: 365 year: 2020 ident: ref75 article-title: GRNet: Gridding residual network for dense point cloud completion publication-title: Proc Eur Conf Comput Vis – ident: ref71 doi: 10.1109/ICCV.2019.00651 – ident: ref67 doi: 10.1109/ICCV48922.2021.01226 – ident: ref59 doi: 10.1109/ICCV48922.2021.01228 – ident: ref41 doi: 10.1109/ICCV.2019.00730 – ident: ref107 doi: 10.1145/3394171.3413648 – year: 2020 ident: ref28 article-title: Cascaded refinement network for point cloud completion with self-supervision publication-title: arXiv 2010 08719 – ident: ref72 doi: 10.1109/CVPR.2019.00985 – start-page: 1 year: 2018 ident: ref108 article-title: Learning localized generative models for 3D point clouds via graph convolution publication-title: Proc Int Conf Learn Represent – ident: ref113 doi: 10.1109/CVPR46437.2021.00736 – ident: ref29 doi: 10.1109/LRA.2020.2994483 – ident: ref43 doi: 10.1007/978-3-030-58558-7_17 – ident: ref133 doi: 10.1109/JETCAS.2018.2885981 – ident: ref2 doi: 10.1109/TPAMI.2020.3005434 – year: 2021 ident: ref114 article-title: HyperPocket: Generative point cloud completion publication-title: arXiv 2102 05973 – ident: ref132 doi: 10.3390/ijgi10070482 – year: 2022 ident: ref63 article-title: PointAttN: You only need attention for point cloud completion publication-title: arXiv 2203 08485 – ident: ref73 doi: 10.1109/CVPR42600.2020.00700 – ident: ref138 doi: 10.1109/3DV50981.2020.00021 – ident: ref65 doi: 10.1109/CCDC.2019.8832956 – ident: ref95 doi: 10.1016/j.neucom.2019.12.032 – ident: ref30 doi: 10.1109/CVPR42600.2020.00201 – year: 2021 ident: ref37 article-title: A conditional point diffusion-refinement paradigm for 3D point cloud completion publication-title: arXiv 2112 03530 – ident: ref130 doi: 10.1061/(ASCE)CP.1943-5487.0000028 – ident: ref116 doi: 10.1109/CVPR52688.2022.00040 – year: 2022 ident: ref6 article-title: Point cloud completion on structured feature map with feedback network publication-title: arXiv 2202 08583 – ident: ref102 doi: 10.1109/CVPR46437.2021.01013 – ident: ref16 doi: 10.1109/CVPR.2019.00910 – year: 2017 ident: ref19 article-title: PointNet++: Deep hierarchical feature learning on point sets in a metric space publication-title: arXiv 1706 02413 – ident: ref87 doi: 10.1117/12.2586422 – ident: ref78 doi: 10.1007/978-3-030-58580-8_5 – ident: ref9 doi: 10.1109/CVPR52688.2022.00177 – year: 2021 ident: ref57 article-title: Relationship-based point cloud completion publication-title: IEEE Trans Vis Comput Graph – ident: ref54 doi: 10.1109/MCG.2021.3065533 – ident: ref117 doi: 10.1109/CVPR46437.2021.01268 – year: 2020 ident: ref53 article-title: Refinement of predicted missing parts enhance point cloud completion publication-title: arXiv 2010 04278 – ident: ref44 doi: 10.1109/CVPR.2018.00295 – year: 2022 ident: ref21 article-title: PMP-Net++: Point cloud completion by transformer-enhanced multi-step point moving paths publication-title: IEEE Trans Pattern Anal Mach Intell – ident: ref123 doi: 10.1109/ICCV48922.2021.01595 – ident: ref85 doi: 10.1109/LRA.2021.3097081 – ident: ref50 doi: 10.1109/CVPR46437.2021.01563 – ident: ref104 doi: 10.1109/TGRS.2021.3105551 – ident: ref68 doi: 10.1109/ICCVW.2019.00506 – ident: ref25 doi: 10.1109/3DV.2018.00088 – year: 2022 ident: ref5 article-title: Reconstruction-aware prior distillation for semi-supervised point cloud completion publication-title: arXiv 2204 09186 – ident: ref38 doi: 10.1109/CVPR.2017.264 – ident: ref47 doi: 10.1016/j.cagd.2020.101925 – year: 2018 ident: ref101 article-title: Point cloud GAN publication-title: arXiv 1810 05795 – volume: 27 start-page: 1 year: 2014 ident: ref91 article-title: Generative adversarial nets publication-title: Proc Adv Neural Inf Process Syst – ident: ref55 doi: 10.1109/ACCESS.2020.2973003 – ident: ref89 doi: 10.1016/j.imavis.2021.104193 – ident: ref45 doi: 10.1016/j.neucom.2021.06.080 – year: 2020 ident: ref90 article-title: PC-RGNN: Point cloud completion and graph neural network for 3D object detection publication-title: arXiv 2012 10412 – year: 2020 ident: ref3 article-title: Deep learning for 3D point cloud understanding: A survey publication-title: arXiv 2009 08920 – ident: ref51 doi: 10.5194/isprs-annals-V-2-2020-933-2020 – ident: ref64 doi: 10.1109/CVPR.2018.00478 – ident: ref112 doi: 10.1109/ICCV48922.2021.00545 – ident: ref88 doi: 10.1109/ICPR48806.2021.9413104 – ident: ref135 doi: 10.1016/j.tust.2010.04.008 – year: 2020 ident: ref106 article-title: Learning geometry-image representation for 3D point cloud generation publication-title: arXiv 2011 14289 – ident: ref36 doi: 10.1109/CVPR46437.2021.00842 – year: 2021 ident: ref1 article-title: A comprehensive survey on point cloud registration publication-title: arXiv 2103 02690 – year: 2020 ident: ref46 article-title: Skeleton-bridged point completion: From global inference to local adjustment publication-title: arXiv 2010 07428 – year: 2022 ident: ref10 article-title: SRPCN: Structure retrieval based point completion network publication-title: arXiv 2202 02669 – ident: ref126 doi: 10.1109/ICCV48922.2021.00964 – ident: ref122 doi: 10.1109/CVPR46437.2021.00738 – ident: ref60 doi: 10.1007/978-3-030-60633-6_27 – ident: ref27 doi: 10.1109/LRA.2020.3048658 – ident: ref103 doi: 10.1109/CVPR42600.2020.00768 – ident: ref48 doi: 10.1109/CVPR.2018.00029 – ident: ref97 doi: 10.1109/CVPR46437.2021.01288 – year: 2021 ident: ref58 article-title: High-fidelity point cloud completion with low-resolution recovery and noise-aware upsampling publication-title: arXiv 2112 11271 – ident: ref49 doi: 10.1109/CVPR.2019.00110 – ident: ref110 doi: 10.1109/CVPR46437.2021.00459 – volume: 36 start-page: 2w year: 2004 ident: ref129 article-title: Terrestrial laser scanning-New perspectives in 3D surveying publication-title: Int Arch Photogramm Remote Sens Spatial Inf Sci – ident: ref70 doi: 10.1109/CVPR.2018.00109 – year: 2020 ident: ref136 article-title: S3CNet: A sparse semantic scene completion network for LiDAR point clouds publication-title: arXiv 2012 09242 – year: 2020 ident: ref137 article-title: Sparse single sweep LiDAR point cloud segmentation via learning contextual shape priors from scene completion publication-title: arXiv 2012 03762 – ident: ref111 doi: 10.1109/TIP.2021.3073318 – ident: ref15 doi: 10.1109/CVPR.2018.00209 – start-page: 1 year: 2020 ident: ref125 article-title: SAUM: Symmetry-aware upsampling module for consistent point cloud completion publication-title: Proc Asian Conf Comput Vis – ident: ref131 doi: 10.1007/s11831-019-09320-4 |
| SSID | ssj0014511 |
| Score | 2.6656287 |
| SecondaryResourceType | review_article |
| Snippet | Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications of 3D computer... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 22862 |
| SubjectTerms | 3D vision Cloud computing completion Computer vision Deep learning Laser radar point cloud Point cloud compression Shape Solid modeling Task analysis Three dimensional models Three-dimensional displays |
| Title | Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis |
| URI | https://ieeexplore.ieee.org/document/9857670 https://www.proquest.com/docview/2747611599 |
| Volume | 23 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PS8MwFA5zJz34a4rTKTl4ErulWdM2R92UKUwEN9hFSpsfKo52zPbiX-9L2o6hIt4KfSmhL837vr73viB0zryYuyERjtAaCEpAhcM51Y4msRFfEX5ii2jGD_5o6t3P2KyBLle9MEopW3ymuubS5vJlJgrzq6zHQ0DHARD0DSBuZa_WKmNgdLasNir1HE5YncF0Ce9N7iZPwAQpBYLKGTNdfWsxyB6q8mMntuHldgeN64mVVSXv3SJPuuLzm2bjf2e-i7YrnImvyoWxhxoq3Udba-qDLfRs9oKlei1L2HGZJcCZxkOlFrgSXn1xriHOSdwf4sfsLc3xYJ4VEpuhRrY7S3HVagCmOE4lrlVODtD09mYyGDnVaQuOgJCfO0FCYpMDZGEgNdGCulL2SSgB0EghFGU6Fl4AbE6EwtVEaT_xJUkk3AZIFMT9Q9RMs1QdIUxc5QLMoYwGRkGNxmAO0dILYqmI5KyNSP3-I1FJkZsTMeaRpSSER8ZlkXFZVLmsjS5WQxalDsdfxi3jgpVh9fbbqFM7Oaq-1I_IsHIfYDHnx7-POkGb5tllCUsHNfNloU4BiOTJmV2BX0vi2MM |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8QwEB5kPagH3-Lqqjl4ErubZpu2OeqqrI8VwRW8SGnzUHFpRduLv95JH4uoiLdCJzR00sz3dWa-AOxzLxZuSKUjjUGCEjDpCMGMY2hsxVekn5RFNKNrf3jnXdzz-xk4nPbCaK3L4jPdtZdlLl9lsrC_ynoiRHQcIEGfxbjP3apba5ozsEpbpToq8xxBeZPDdKnojc_Ht8gFGUOKKji3fX1folB5rMqPvbgMMGdLMGqmVtWVvHSLPOnKj2-qjf-d-zIs1kiTHFVLYwVmdLoKC1_0B9fgwe4Gb_qpKmInVZ6AZIacaP1KaunVR-cYI50i_RNykz2nORlMskIRO9QKd2cpqZsN0JTEqSKNzsk63J2djgdDpz5vwZEY9HMnSGhss4A8DJShRjJXqT4NFUIaJaVm3MTSC5DPyVC6hmrjJ76iicLbCIqCuL8BrTRL9SYQ6moXgQ7jLLAaaixGc4yXXhArTZXgbaDN-49kLUZuz8SYRCUpoSKyLousy6LaZW04mA55rZQ4_jJesy6YGtZvvw2dxslR_a2-R5aX-wiMhdj6fdQezA3Ho6vo6vz6chvm7XOqgpYOtPK3Qu8gLMmT3XI1fgLFKdwM |
| 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=Comprehensive+Review+of+Deep+Learning-Based+3D+Point+Cloud+Completion+Processing+and+Analysis&rft.jtitle=IEEE+transactions+on+intelligent+transportation+systems&rft.au=Fei%2C+Ben&rft.au=Yang%2C+Weidong&rft.au=Chen%2C+Wen-Ming&rft.au=Li%2C+Zhijun&rft.date=2022-12-01&rft.issn=1524-9050&rft.eissn=1558-0016&rft.volume=23&rft.issue=12&rft.spage=22862&rft.epage=22883&rft_id=info:doi/10.1109%2FTITS.2022.3195555&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TITS_2022_3195555 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1524-9050&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1524-9050&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1524-9050&client=summon |