{"id":"https://openalex.org/W4411171863","doi":"https://doi.org/10.1109/tcsvt.2025.3578474","title":"VPA: Multi-Modal Virtual Point Augmentation for 3D Object Detection","display_name":"VPA: Multi-Modal Virtual Point Augmentation for 3D Object Detection","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4411171863","doi":"https://doi.org/10.1109/tcsvt.2025.3578474"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3578474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3578474","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111813251","display_name":"Jianping Zhong","orcid":"https://orcid.org/0009-0008-3091-8791"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Zhong","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044171641","display_name":"Zhaobo Qi","orcid":"https://orcid.org/0000-0001-9196-9818"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaobo Qi","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"],"raw_orcid":"https://orcid.org/0000-0001-9196-9818","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017318126","display_name":"Kaiwen Duan","orcid":"https://orcid.org/0000-0002-8663-7429"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiwen Duan","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8663-7429","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071230372","display_name":"Yuanrong Xu","orcid":"https://orcid.org/0000-0002-9457-7956"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanrong Xu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014774434","display_name":"Weigang Zhang","orcid":"https://orcid.org/0000-0003-0042-7074"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weigang Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"],"raw_orcid":"https://orcid.org/0000-0003-0042-7074","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7542-296X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1465762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":"12","first_page":"12410","last_page":"12425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6955795884132385},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6086390018463135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.546507716178894},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5420047640800476},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5234379768371582},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4457366466522217},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.44199782609939575},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3472236394882202},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.313173770904541},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16980531811714172}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955795884132385},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6086390018463135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.546507716178894},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5420047640800476},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5234379768371582},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4457366466522217},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.44199782609939575},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3472236394882202},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.313173770904541},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16980531811714172},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3578474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3578474","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1535954828","display_name":null,"funder_award_id":"62306092","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3840657713","display_name":null,"funder_award_id":"62441232","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4199693610","display_name":null,"funder_award_id":"62236008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5430478364","display_name":null,"funder_award_id":"ZR2023QF052","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G6212863906","display_name":null,"funder_award_id":"U21B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7371018157","display_name":null,"funder_award_id":"ZR2024QF066","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G89782005","display_name":null,"funder_award_id":"62476068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2555618208","https://openalex.org/W2897529137","https://openalex.org/W2949708697","https://openalex.org/W2963727135","https://openalex.org/W2968296999","https://openalex.org/W2982770724","https://openalex.org/W3003618643","https://openalex.org/W3008105217","https://openalex.org/W3017930107","https://openalex.org/W3034314779","https://openalex.org/W3035049382","https://openalex.org/W3035172746","https://openalex.org/W3035346742","https://openalex.org/W3035363555","https://openalex.org/W3035461736","https://openalex.org/W3035574168","https://openalex.org/W3108426750","https://openalex.org/W3109395584","https://openalex.org/W3118341329","https://openalex.org/W3166089996","https://openalex.org/W3167095230","https://openalex.org/W3177276051","https://openalex.org/W3209639308","https://openalex.org/W3215100485","https://openalex.org/W4200629389","https://openalex.org/W4225793049","https://openalex.org/W4226098442","https://openalex.org/W4226280874","https://openalex.org/W4282937133","https://openalex.org/W4286901804","https://openalex.org/W4288064589","https://openalex.org/W4312437143","https://openalex.org/W4312707458","https://openalex.org/W4312894406","https://openalex.org/W4312934050","https://openalex.org/W4312953085","https://openalex.org/W4313142137","https://openalex.org/W4321770545","https://openalex.org/W4327522797","https://openalex.org/W4376607688","https://openalex.org/W4382464460","https://openalex.org/W4382469134","https://openalex.org/W4383066393","https://openalex.org/W4384787373","https://openalex.org/W4385151926","https://openalex.org/W4385245566","https://openalex.org/W4385804883","https://openalex.org/W4385975752","https://openalex.org/W4386066365","https://openalex.org/W4386075854","https://openalex.org/W4386076127","https://openalex.org/W4386076253","https://openalex.org/W4386076667","https://openalex.org/W4390479122","https://openalex.org/W4390872227","https://openalex.org/W4390873604","https://openalex.org/W4390874155","https://openalex.org/W4390874213","https://openalex.org/W4391877825","https://openalex.org/W4392143229","https://openalex.org/W4402703030","https://openalex.org/W4402961790","https://openalex.org/W4415798919"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2737719445","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2898210368","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Integrating":[0],"LiDAR":[1],"and":[2,46,86,97,111,129,138,182,211,222,238,245],"camera":[3],"data":[4],"is":[5,255],"crucial":[6],"for":[7,153],"precise":[8],"3D":[9,32,44,63,75,165,184],"object":[10,64],"detection.":[11,55],"Existing":[12],"methods":[13],"resort":[14],"to":[15,27,72,133,144,148,206],"augmenting":[16],"virtual":[17,40,81,163,201],"points":[18,41,82],"from":[19,95,178],"2D":[20],"image":[21,96,180],"space":[22],"in":[23,187],"a":[24,61,140],"random":[25],"manner":[26,190],"complete":[28],"the":[29,74,118,126,154,159,162,169,172,175,179,183,197,200,207,219,226,250],"appearance":[30],"of":[31,161,199,228],"objects":[33],"with":[34,83,235],"sparse":[35],"points.":[36,202],"However,":[37],"these":[38],"augmented":[39],"have":[42],"unreasonable":[43],"positions":[45],"representations,":[47],"which":[48,231],"brings":[49],"serious":[50],"negative":[51],"effects":[52],"on":[53,125,218,249],"accurate":[54,84,151],"To":[56],"this":[57],"end,":[58],"we":[59],"introduce":[60],"general":[62],"detection":[65],"framework":[66],"called":[67],"Virtual":[68],"Point":[69],"Augmenting":[70],"(VPA)":[71],"enrich":[73],"point":[76,98,121],"cloud":[77,99],"by":[78],"controllably":[79],"generating":[80],"depth":[85,147,152],"position":[87,185],"information":[88],"as":[89,91],"well":[90],"domain-gap-eliminated":[92],"multi-modal":[93,170],"representations":[94],"spaces.":[100],"VPA":[101,205],"contains":[102],"two":[103],"core":[104],"designs,":[105],"namely":[106],"Hybrid":[107],"Sampling":[108],"Method":[109],"(HSM)":[110],"Fine-Grained":[112],"Cross-modal":[113,214],"Fusion":[114],"(FGCF).":[115],"HSM":[116],"uses":[117],"constructed":[119],"seed":[120,136,155],"distribution":[122],"map":[123,132],"based":[124],"edge":[127],"score":[128,131],"mask":[130],"sample":[134,145],"high-quality":[135],"points,":[137,156],"employs":[139],"feature":[141,177,186],"similarity":[142],"function":[143],"withkneighbors\u2019":[146],"obtain":[149],"more":[150],"thereby":[157,194],"enhancing":[158],"quality":[160],"points\u2019":[164],"positions.":[166],"FGCF":[167],"fuses":[168],"features,i.e.,":[171],"semantic":[173],"feature,":[174],"geometric":[176],"space,":[181],"an":[188],"adaptive":[189],"using":[191,242],"self-attention":[192],"mechanism,":[193],"further":[195],"improving":[196],"representation":[198],"We":[203],"apply":[204],"LiDAR-based":[208],"method":[209,213],"CenterPoint":[210],"fusion-based":[212],"transformer.":[215],"Experimental":[216],"results":[217],"nuScenes,":[220],"KITTI,":[221],"Waymo":[223],"benchmarks":[224],"validate":[225],"efficiency":[227],"our":[229],"VPA,":[230],"achieves":[232],"promising":[233],"performance":[234],"72.9%":[236],"mAP":[237],"74.8%":[239],"NDS":[240],"without":[241],"test-time":[243],"augmentation":[244],"model":[246],"ensemble":[247],"techniques":[248],"nuScenes":[251],"test":[252],"set.":[253],"Code":[254],"available":[256],"at":[257],"https://github.com/jianpingZhonggit/vpa.git.":[258]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}