LVP: Leverage Virtual Points in Multimodal Early Fusion for 3-D Object Detection
Due to the sparsity and occlusion of point clouds, pure point cloud detection has limited effectiveness in detecting such samples. Researchers have been actively exploring the fusion of multimodal data, attempting to address the bottleneck issue based on LiDAR. In particular, virtual points, generat...
Saved in:
| Published in: | IEEE transactions on geoscience and remote sensing Vol. 63; pp. 1 - 15 |
|---|---|
| Main Authors: | , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
New York
IEEE
2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 0196-2892, 1558-0644 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Due to the sparsity and occlusion of point clouds, pure point cloud detection has limited effectiveness in detecting such samples. Researchers have been actively exploring the fusion of multimodal data, attempting to address the bottleneck issue based on LiDAR. In particular, virtual points, generated through depth completion from front-view RGB image, offer the potential for better integration with point clouds. Nevertheless, recent approaches fuse these two modalities in the region of interest (RoI), which limits the fusion effectiveness due to the inaccurate RoI region issue in the point cloud's branch, especially in hard samples. To overcome it and unleash the potential of virtual points, while combining late fusion, we present leverage virtual point (LVP), a high-performance 3-D object detector which LVPs in early fusion to enhance the quality of RoI generation. LVP consists of three early fusion modules: virtual points painting (VPP), virtual points auxiliary (VPA), and virtual points completion (VPC) to achieve point-level fusion and global-level fusion. The integration of these modules effectively improves occlusion handling and improves the detection of distant small objects. In the KITTI benchmark, LVP achieves 85.45% 3-D mAP. As for large dataset nuScenes, we could improve the detection accuracy of large objects by compensating for errors in depth estimation. Without whistles and bells, these results establish LVP as an impressive solution for a 3-D outdoor object detection algorithm. |
|---|---|
| AbstractList | Due to the sparsity and occlusion of point clouds, pure point cloud detection has limited effectiveness in detecting such samples. Researchers have been actively exploring the fusion of multimodal data, attempting to address the bottleneck issue based on LiDAR. In particular, virtual points, generated through depth completion from front-view RGB image, offer the potential for better integration with point clouds. Nevertheless, recent approaches fuse these two modalities in the region of interest (RoI), which limits the fusion effectiveness due to the inaccurate RoI region issue in the point cloud's branch, especially in hard samples. To overcome it and unleash the potential of virtual points, while combining late fusion, we present leverage virtual point (LVP), a high-performance 3-D object detector which LVPs in early fusion to enhance the quality of RoI generation. LVP consists of three early fusion modules: virtual points painting (VPP), virtual points auxiliary (VPA), and virtual points completion (VPC) to achieve point-level fusion and global-level fusion. The integration of these modules effectively improves occlusion handling and improves the detection of distant small objects. In the KITTI benchmark, LVP achieves 85.45% 3-D mAP. As for large dataset nuScenes, we could improve the detection accuracy of large objects by compensating for errors in depth estimation. Without whistles and bells, these results establish LVP as an impressive solution for a 3-D outdoor object detection algorithm. |
| Author | Liu, Zhaoliang Zeng, Binghui Cai, Guorong Song, Ziying Li, Jonathan Wang, Zongyue Chen, Yidong |
| Author_xml | – sequence: 1 givenname: Yidong orcidid: 0000-0001-6839-661X surname: Chen fullname: Chen, Yidong email: chenyidong2022@163.com organization: Computer Engineering College, Jimei University, Xiamen, China – sequence: 2 givenname: Guorong orcidid: 0000-0001-8091-271X surname: Cai fullname: Cai, Guorong email: guorongcai@jmu.edu.cn organization: Office of Science and Research, Jimei University, Xiamen, China – sequence: 3 givenname: Ziying orcidid: 0000-0001-5539-2599 surname: Song fullname: Song, Ziying email: songziying@bjtu.edu.cn organization: School of Computer and Information Technology, Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China – sequence: 4 givenname: Zhaoliang orcidid: 0009-0004-9791-2846 surname: Liu fullname: Liu, Zhaoliang email: 202211810027@jmu.edu.cn organization: Computer Engineering College, Jimei University, Xiamen, China – sequence: 5 givenname: Binghui orcidid: 0009-0007-5851-8485 surname: Zeng fullname: Zeng, Binghui email: zengbinghui@jmu.edu.cn organization: Computer Engineering College, Jimei University, Xiamen, China – sequence: 6 givenname: Jonathan orcidid: 0000-0001-7899-0049 surname: Li fullname: Li, Jonathan email: junli@uwaterloo.ca organization: Department of Geography and Environmental Management and the Department of System Design Engineering, University of Waterloo, Waterloo, ON, Canada – sequence: 7 givenname: Zongyue orcidid: 0000-0003-2409-7065 surname: Wang fullname: Wang, Zongyue email: wangzongyue@jmu.edu.cn organization: Computer Engineering College, Jimei University, Xiamen, China |
| BookMark | eNp9kF9LwzAUxYNMcJt-AMGHgM-dN0mTNr7J_ilUNnTutaRtIhldO9NU2Le3ZXsQH3w6cO45915-IzSo6kojdEtgQgjIh83y7X1CgYYTxolksbhAQ8J5HIAIwwEaApEioLGkV2jUNDsAEnISDdE62a4fcaK_tVOfGm-t860q8bq2lW-wrfBrW3q7r4vOnCtXHvGibWxdYVM7zIIZXmU7nXs8076TbnCNLo0qG31z1jH6WMw30-cgWS1fpk9JkFMZ-sAwk0dFqIw2JKJABOcZRHHnilwwLgRXBWfATAw5kzLSGYgCMqpoN1RUsjG6P-09uPqr1Y1Pd3Xrqu5kyggHzgUR0KWiUyp3ddM4bdLcetX_6Z2yZUog7fGlPb60x5ee8XVN8qd5cHav3PHfzt2pY7XWv_IxhEJS9gPfuntm |
| CODEN | IGRSD2 |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2025_3553372 crossref_primary_10_1109_JSEN_2025_3582040 |
| Cites_doi | 10.1109/CVPR52729.2023.02074 10.1109/ICCV48922.2021.00272 10.1109/CVPR52729.2023.02076 10.1109/CVPR42600.2020.01189 10.1109/TPAMI.2020.2977026 10.1109/TGRS.2023.3331893 10.1109/CVPR52729.2023.00500 10.1109/ICIP.2019.8803572 10.1109/ICCV.2019.00987 10.1109/CVPR52733.2024.01451 10.1109/CVPR52688.2022.00534 10.1109/ICCV48922.2021.00315 10.1007/978-3-031-20074-8_39 10.3390/s18103337 10.1109/CVPR42600.2020.01054 10.1007/978-3-030-58555-6_3 10.1007/978-3-030-58583-9_43 10.1109/TGRS.2023.3250229 10.1109/CVPR.2019.01298 10.1109/CVPR.2017.691 10.1109/TGRS.2022.3203163 10.1016/j.jag.2021.102406 10.1109/ICRA48506.2021.9561035 10.1109/CVPR.2012.6248074 10.1109/TGRS.2023.3271020 10.1109/CVPR52688.2022.01838 10.1109/CVPR42600.2020.01105 10.1609/aaai.v37i3.25380 10.1109/CVPR46437.2021.01426 10.1109/CVPR52729.2023.01681 10.1109/ICCV.2019.00667 10.1109/TITS.2021.3133476 10.1109/CVPR.2015.7298655 10.1109/CVPR46437.2021.01161 10.1007/978-3-031-72998-0_13 10.1109/CVPR52729.2023.00503 10.1109/CVPR52733.2024.01425 10.1609/aaai.v33i01.33019267 10.1109/CVPR42600.2020.00252 10.1109/CVPR52729.2023.00897 10.1609/aaai.v36i3.20194 10.1109/CVPR52729.2023.01296 10.1109/CVPR42600.2020.00466 10.1609/aaai.v35i2.16207 10.1109/CVPRW50498.2020.00109 10.1109/CVPR.2018.00472 10.1109/ICCV51070.2023.00575 10.1109/CVPR52688.2022.00535 10.1007/978-3-030-58568-6_12 10.1109/TGRS.2022.3174483 10.1109/TITS.2024.3357841 10.1109/CVPR52733.2024.01418 10.1609/aaai.v38i3.28016 10.1609/aaai.v34i07.6837 10.1109/CVPR.2019.00086 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025 |
| DBID | 97E RIA RIE AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M |
| DOI | 10.1109/TGRS.2024.3519386 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace |
| DatabaseTitle | CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Water Resources Abstracts Environmental Sciences and Pollution Management |
| DatabaseTitleList | Aerospace Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore Digital Libary (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Physics |
| EISSN | 1558-0644 |
| EndPage | 15 |
| ExternalDocumentID | 10_1109_TGRS_2024_3519386 10804692 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 42371457; 42301468 funderid: 10.13039/501100001809 – fundername: Key Project of Natural Science Foundation of Fujian Province, China grantid: 2022J02045 – fundername: Natural Science Foundation of Xiamen, China grantid: 3502Z20227048; 3502Z20227049 – fundername: Natural Science Foundation of Fujian Province, China grantid: 2022J01337; 2022J01819; 2023J01801; 2023J01799; 2022J05157; 2022J011394 – fundername: Open Competition for Innovative Projects of Xiamen, China grantid: 3502Z20231038 – fundername: Science and Technology Program of Xiamen, China grantid: 2022CXY0302 funderid: 10.13039/501100018556 – fundername: Start-Up Fund of Jimei University grantid: ZQ2022031 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 Y6R AAYXX CITATION 7UA 8FD AARMG C1K F1W FR3 H8D H96 KR7 L.G L7M |
| ID | FETCH-LOGICAL-c294t-f3fc7d4afef17201655b0783fc6c635665ad5303f80c3997eb06d0b2a2356a293 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 5 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001386444900013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0196-2892 |
| IngestDate | Mon Jun 30 10:20:32 EDT 2025 Sat Nov 29 06:53:17 EST 2025 Tue Nov 18 21:35:27 EST 2025 Wed Nov 19 08:27:09 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| 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-c294t-f3fc7d4afef17201655b0783fc6c635665ad5303f80c3997eb06d0b2a2356a293 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0001-5539-2599 0009-0007-5851-8485 0000-0001-8091-271X 0000-0001-7899-0049 0000-0001-6839-661X 0000-0003-2409-7065 0009-0004-9791-2846 |
| PQID | 3150556160 |
| PQPubID | 85465 |
| PageCount | 15 |
| ParticipantIDs | ieee_primary_10804692 proquest_journals_3150556160 crossref_citationtrail_10_1109_TGRS_2024_3519386 crossref_primary_10_1109_TGRS_2024_3519386 |
| PublicationCentury | 2000 |
| PublicationDate | 20250000 2025-00-00 20250101 |
| PublicationDateYYYYMMDD | 2025-01-01 |
| PublicationDate_xml | – year: 2025 text: 20250000 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on geoscience and remote sensing |
| PublicationTitleAbbrev | TGRS |
| PublicationYear | 2025 |
| 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 | ref13 ref12 ref56 ref15 ref53 ref52 ref11 ref55 ref10 ref54 Yin (ref14); 34 ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref48 ref47 ref42 ref41 ref44 ref43 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 |
| References_xml | – ident: ref13 doi: 10.1109/CVPR52729.2023.02074 – ident: ref55 doi: 10.1109/ICCV48922.2021.00272 – ident: ref30 doi: 10.1109/CVPR52729.2023.02076 – ident: ref41 doi: 10.1109/CVPR42600.2020.01189 – ident: ref21 doi: 10.1109/TPAMI.2020.2977026 – ident: ref8 doi: 10.1109/TGRS.2023.3331893 – ident: ref29 doi: 10.1109/CVPR52729.2023.00500 – ident: ref52 doi: 10.1109/ICIP.2019.8803572 – ident: ref34 doi: 10.1109/ICCV.2019.00987 – ident: ref9 doi: 10.1109/CVPR52733.2024.01451 – ident: ref12 doi: 10.1109/CVPR52688.2022.00534 – ident: ref32 doi: 10.1109/ICCV48922.2021.00315 – ident: ref33 doi: 10.1007/978-3-031-20074-8_39 – ident: ref26 doi: 10.3390/s18103337 – ident: ref36 doi: 10.1109/CVPR42600.2020.01054 – ident: ref43 doi: 10.1007/978-3-030-58555-6_3 – ident: ref53 doi: 10.1007/978-3-030-58583-9_43 – ident: ref5 doi: 10.1109/TGRS.2023.3250229 – ident: ref27 doi: 10.1109/CVPR.2019.01298 – ident: ref16 doi: 10.1109/CVPR.2017.691 – ident: ref2 doi: 10.1109/TGRS.2022.3203163 – ident: ref22 doi: 10.1016/j.jag.2021.102406 – ident: ref47 doi: 10.1109/ICRA48506.2021.9561035 – volume: 34 start-page: 16494 volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS) ident: ref14 article-title: Multimodal virtual point 3D detection – ident: ref46 doi: 10.1109/CVPR.2012.6248074 – ident: ref7 doi: 10.1109/TGRS.2023.3271020 – ident: ref24 doi: 10.1109/CVPR52688.2022.01838 – ident: ref23 doi: 10.1109/CVPR42600.2020.01105 – ident: ref31 doi: 10.1609/aaai.v37i3.25380 – ident: ref19 doi: 10.1109/CVPR46437.2021.01426 – ident: ref45 doi: 10.1109/CVPR52729.2023.01681 – ident: ref48 doi: 10.1109/ICCV.2019.00667 – ident: ref42 doi: 10.1109/TITS.2021.3133476 – ident: ref49 doi: 10.1109/CVPR.2015.7298655 – ident: ref18 doi: 10.1109/CVPR46437.2021.01161 – ident: ref1 doi: 10.1007/978-3-031-72998-0_13 – ident: ref39 doi: 10.1109/CVPR52729.2023.00503 – ident: ref3 doi: 10.1109/CVPR52733.2024.01425 – ident: ref51 doi: 10.1609/aaai.v33i01.33019267 – ident: ref38 doi: 10.1109/CVPR42600.2020.00252 – ident: ref40 doi: 10.1109/CVPR52729.2023.00897 – ident: ref37 doi: 10.1609/aaai.v36i3.20194 – ident: ref28 doi: 10.1109/CVPR52729.2023.01296 – ident: ref44 doi: 10.1109/CVPR42600.2020.00466 – ident: ref35 doi: 10.1609/aaai.v35i2.16207 – ident: ref50 doi: 10.1109/CVPRW50498.2020.00109 – ident: ref25 doi: 10.1109/CVPR.2018.00472 – ident: ref17 doi: 10.1109/ICCV51070.2023.00575 – ident: ref56 doi: 10.1109/CVPR52688.2022.00535 – ident: ref15 doi: 10.1007/978-3-030-58568-6_12 – ident: ref6 doi: 10.1109/TGRS.2022.3174483 – ident: ref4 doi: 10.1109/TITS.2024.3357841 – ident: ref10 doi: 10.1109/CVPR52733.2024.01418 – ident: ref11 doi: 10.1609/aaai.v38i3.28016 – ident: ref54 doi: 10.1609/aaai.v34i07.6837 – ident: ref20 doi: 10.1109/CVPR.2019.00086 |
| SSID | ssj0014517 |
| Score | 2.5100598 |
| Snippet | Due to the sparsity and occlusion of point clouds, pure point cloud detection has limited effectiveness in detecting such samples. Researchers have been... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1 |
| SubjectTerms | 3-D object detection Accuracy Algorithms autonomous driving Cloud computing early fusion Effectiveness Feature extraction Geoscience and remote sensing Laser radar Lidar Modules multimodal Object detection Object recognition Occlusion Point cloud compression Proposals Sensory integration Shape Three dimensional models Three-dimensional displays Valproic acid virtual points |
| Title | LVP: Leverage Virtual Points in Multimodal Early Fusion for 3-D Object Detection |
| URI | https://ieeexplore.ieee.org/document/10804692 https://www.proquest.com/docview/3150556160 |
| Volume | 63 |
| WOSCitedRecordID | wos001386444900013&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 Xplore Digital Libary (IEL) customDbUrl: eissn: 1558-0644 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014517 issn: 0196-2892 databaseCode: RIE dateStart: 19800101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA86FPTgx5w4nZKDJ6Fblqbp6k2c08OYQ-fYraRpAgXtZOv8-30v68ZAFLyU0iZQ8tKX3_v4vUfINajdFGC49QJhrCd4GnlRx9dwkZapQCqZOkn3w8GgM5lEw5Ks7rgwxhiXfGaaeOti-elUL9BV1sJ8ODDnQONuh6FckrXWIQMRtEtutPTAiuBlCLPNotbo8eUVTEEumtiOzkfe9MYh5Lqq_FDF7nzpHf7zy47IQQkk6d1S8sdky-RVsr9RXrBKdl16p56fkGF_PLylfQP7FvQHHWczpI3Q4TTLiznNcup4uB_TFB66kse0t0A3GgVIS32vS58T9NfQrilc6lZeI2-9h9H9k1f2UvA0j0ThWd_qMBXKGguQBTlMQYIRPKulxhJ1MlBpAMeZ7TANmCU0CZMpS7ji8FIBJjgllXyamzNCQ8ESwyyGWK0wIVNCcAWwMGDaRlbxOmGrxY11WWgc-128x87gYFGM8ohRHnEpjzq5WU_5XFbZ-GtwDQWwMXC59nXSWIkwLn_EeewD4MUOoJKd_zLtguxx7Onr3CoNUilmC3NJdvRXkc1nV26PfQNkqsvR |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD6IF9QHrxPnNQ8-CdUsTdvVN1HnxDqHTvGtpGkCA-1k6_z9npNVGYiCL6W0CZR86cm5fecAHKHYzVENt14gjfWkyGMvbvoaL6HlKghVmDukk6jTab68xN2KrO64MMYYl3xmTujWxfLzgR6Tq-yU8uHQnEOJOxdIKfiErvUdNJBBo2JHhx7aEaIKYjZ4fNq7fnhEY1DIE2pI5xNzeuoYcn1Vfghjd8K0Vv_5bWuwUqmS7HyC_TrMmGIDlqcKDG7Agkvw1KNN6CbP3TOWGNy5KEHYc39IxBHWHfSLcsT6BXNM3LdBjg9d0WPWGpMjjaFSy3zvkt1n5LFhl6Z0yVtFDZ5aV72Ltld1U_C0iGXpWd_qKJfKGotKC7GYgoxieFaHmorUhYHKAzzQbJNr1Foik_Ew55lQAl8q1Aq2YLYYFGYbWCR5ZrilIKuVJuIKwVCoGAZc29gqUQf-tbiprkqNU8eL19SZHDxOCY-U8EgrPOpw_D3lfVJn46_BNQJgauBk7euw9wVhWv2Ko9RHlZd6gIZ855dph7DY7t0laXLTud2FJUEdfp2TZQ9my-HY7MO8_ij7o-GB22-fLL_PGA |
| 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=LVP%3A+Leverage+Virtual+Points+in+Multimodal+Early+Fusion+for+3-D+Object+Detection&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Chen%2C+Yidong&rft.au=Cai%2C+Guorong&rft.au=Song%2C+Ziying&rft.au=Liu%2C+Zhaoliang&rft.date=2025&rft.pub=IEEE&rft.issn=0196-2892&rft.volume=63&rft.spage=1&rft.epage=15&rft_id=info:doi/10.1109%2FTGRS.2024.3519386&rft.externalDocID=10804692 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-2892&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-2892&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-2892&client=summon |