{"id":"https://openalex.org/W7160271224","doi":"https://doi.org/10.1109/wacv61042.2026.00635","title":"V2XScene: Multi-View Consistent 3D Scene Simulation for Collaborative Perception","display_name":"V2XScene: Multi-View Consistent 3D Scene Simulation for Collaborative Perception","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160271224","doi":"https://doi.org/10.1109/wacv61042.2026.00635"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5023033518","display_name":"Y Li","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfei Li","raw_affiliation_strings":["Southern University of Science and Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687951","display_name":"Yi Gong","orcid":"https://orcid.org/0000-0001-7392-8991"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Gong","raw_affiliation_strings":["Southern University of Science and Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100617494","display_name":"Yuan Zeng","orcid":"https://orcid.org/0000-0002-5260-8064"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zeng","raw_affiliation_strings":["Shenzhen Technology University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380"]}]}],"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":0.53373366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6569","last_page":"6579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.3562000095844269,"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":0.3562000095844269,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.07829999923706055,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T12290","display_name":"Human Motion and Animation","score":0.07599999755620956,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4602000117301941},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.33239999413490295},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2946000099182129},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.28859999775886536},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2782999873161316},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.27399998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5666000247001648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4659000039100647},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4309999942779541},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2982681137","https://openalex.org/W2996759437","https://openalex.org/W3201193904","https://openalex.org/W4200150166","https://openalex.org/W4286544732","https://openalex.org/W4312604822","https://openalex.org/W4312713450","https://openalex.org/W4312933868","https://openalex.org/W4312939270","https://openalex.org/W4385318467","https://openalex.org/W4386076483","https://openalex.org/W4390872473","https://openalex.org/W4400822286","https://openalex.org/W4401784158","https://openalex.org/W4402727396","https://openalex.org/W4402727875","https://openalex.org/W4402727915","https://openalex.org/W4402754225","https://openalex.org/W4404722496","https://openalex.org/W4409366191","https://openalex.org/W4409368390","https://openalex.org/W4413146238","https://openalex.org/W4413146851","https://openalex.org/W4413147870","https://openalex.org/W7105701437","https://openalex.org/W7133205559","https://openalex.org/W7160047122","https://openalex.org/W7160098870","https://openalex.org/W7160115557"],"related_works":[],"abstract_inverted_index":{"Realistic":[0],"scene":[1,70],"simulation":[2],"is":[3],"a":[4,67,95,109,122],"promising":[5],"way":[6],"to":[7],"improve":[8],"autonomous":[9],"driving.":[10],"While":[11],"existing":[12],"diffusion-based":[13],"2D":[14],"augmentation":[15],"and":[16,34,54,86,118,121,129,142],"3D":[17,68,82,105,110],"asset":[18,84,107],"libraries":[19],"show":[20],"potential":[21],"for":[22,41,103,114,126],"synthesizing":[23],"diverse":[24],"driving":[25,69,144],"scenarios,":[26],"they":[27],"often":[28],"struggle":[29],"with":[30],"multi-view":[31,88,140],"photorealistic":[32],"rendering":[33],"consistency.":[35],"These":[36],"issues":[37],"are":[38],"particularly":[39],"challenging":[40],"vehicle-to-everything":[42],"(V2X)":[43],"collaborative":[44,77],"perception,":[45],"since":[46],"its":[47],"effectiveness":[48],"relies":[49],"on":[50],"precise":[51],"geometric":[52],"alignment":[53],"visual":[55,96],"coherence":[56],"across":[57],"multiple":[58],"viewpoints.":[59],"To":[60],"address":[61],"these":[62],"challenges,":[63],"we":[64],"propose":[65],"V2XScene,":[66],"editing":[71],"framework.":[72],"This":[73],"framework":[74],"enhances":[75],"V2X":[76,149],"perception":[78,150],"by":[79],"enabling":[80],"high-quality":[81],"vehicle":[83,106,115,131],"generation":[85,101],"consistent":[87,141],"insertion.":[89,132],"V2XScene":[90,137],"consists":[91],"of":[92],"three":[93],"components:":[94],"question":[97],"answering":[98],"(VQA)":[99],"guided":[100],"module":[102,113,125],"query-driven":[104],"synthesis;":[108],"object":[111],"mapping":[112],"placement":[116],"optimization":[117],"occlusion":[119],"reasoning;":[120],"realistic":[123,143],"insertion":[124],"lighting":[127],"estimation":[128],"virtual":[130],"Extensive":[133],"experiments":[134],"demonstrate":[135],"that":[136],"can":[138],"generate":[139],"scenes,":[145],"which":[146],"significantly":[147],"improves":[148],"accuracy.":[151]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}