{"id":"https://openalex.org/W4408355340","doi":"https://doi.org/10.1109/icassp49660.2025.10887542","title":"Object-level Data Augmentation for Visual 3D Object Detection in Autonomous Driving","display_name":"Object-level Data Augmentation for Visual 3D Object Detection in Autonomous Driving","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355340","doi":"https://doi.org/10.1109/icassp49660.2025.10887542"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5027015252","display_name":"Haoran Cheng","orcid":"https://orcid.org/0000-0002-1736-1430"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoran Cheng","raw_affiliation_strings":["Zhejiang University,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101494816","display_name":"Junkai Xu","orcid":"https://orcid.org/0000-0002-6366-8863"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junkai Xu","raw_affiliation_strings":["Zhejiang University,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100612023","display_name":"Liang Peng","orcid":"https://orcid.org/0000-0002-9831-2787"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Peng","raw_affiliation_strings":["FABU Inc,Hangzhou,China,310030"],"affiliations":[{"raw_affiliation_string":"FABU Inc,Hangzhou,China,310030","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343279","display_name":"Yang Zheng","orcid":"https://orcid.org/0000-0002-3775-6739"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Yang","raw_affiliation_strings":["FABU Inc,Hangzhou,China,310030"],"affiliations":[{"raw_affiliation_string":"FABU Inc,Hangzhou,China,310030","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102013345","display_name":"Xiaofei He","orcid":"https://orcid.org/0009-0001-9107-2354"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei He","raw_affiliation_strings":["Zhejiang University,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101833492","display_name":"Boxi Wu","orcid":"https://orcid.org/0000-0003-4494-193X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boxi Wu","raw_affiliation_strings":["Zhejiang University,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027015252"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04370346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9829000234603882,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9829000234603882,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.939300000667572,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9111999869346619,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/computer-science","display_name":"Computer science","score":0.7716879844665527},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6773750185966492},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6759054064750671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6142082810401917},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5863752961158752},{"id":"https://openalex.org/keywords/deep-sky-object","display_name":"Deep-sky object","score":0.42742660641670227},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.323733925819397},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.14901301264762878},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09057357907295227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716879844665527},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6773750185966492},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6759054064750671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6142082810401917},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5863752961158752},{"id":"https://openalex.org/C201276399","wikidata":"https://www.wikidata.org/wiki/Q249389","display_name":"Deep-sky object","level":3,"score":0.42742660641670227},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.323733925819397},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.14901301264762878},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09057357907295227}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2331128040","https://openalex.org/W2963271314","https://openalex.org/W3035049382","https://openalex.org/W3035574168","https://openalex.org/W3108325989","https://openalex.org/W3109240920","https://openalex.org/W3173668541","https://openalex.org/W3176319743","https://openalex.org/W3183784042","https://openalex.org/W3204439495","https://openalex.org/W3211081199","https://openalex.org/W4212931966","https://openalex.org/W4214558638","https://openalex.org/W4312461898","https://openalex.org/W4367146742","https://openalex.org/W4382468453","https://openalex.org/W4390872581","https://openalex.org/W4390872833","https://openalex.org/W6751795773","https://openalex.org/W6794141403","https://openalex.org/W6810907425","https://openalex.org/W6811230113"],"related_works":["https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W4401416707","https://openalex.org/W2048280641","https://openalex.org/W4389065903","https://openalex.org/W2026565050","https://openalex.org/W2913842502","https://openalex.org/W4282961848","https://openalex.org/W2082494009","https://openalex.org/W2137482773"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,17,49],"plays":[2],"an":[3,46],"important":[4],"role":[5],"in":[6],"visual-based":[7],"3D":[8,91,109,160],"object":[9,96,161],"detection.":[10],"Existing":[11],"detectors":[12],"typically":[13],"employ":[14],"image/BEV-level":[15],"data":[16,48],"techniques,":[18],"failing":[19],"to":[20,84,105,157],"utilize":[21],"flexible":[22,95],"object-level":[23,47,139],"augmentations":[24],"because":[25],"of":[26,37,138],"2D-3D":[27],"inconsistencies.":[28],"This":[29,80],"limitation":[30],"hinders":[31],"us":[32],"from":[33,70,132],"increasing":[34],"the":[35,62,86,107,129,136,150,165],"diversity":[36],"training":[38],"data.":[39],"To":[40,148],"alleviate":[41],"this":[42],"issue,":[43],"we":[44,60,99,153],"propose":[45],"approach":[50,81],"that":[51],"incorporates":[52],"scene":[53,57,63,103,110,125],"reconstruction":[54],"and":[55,64,72,116],"neural":[56,102],"rendering.":[58],"Specifically,":[59],"reconstruct":[61],"objects":[65],"by":[66],"extracting":[67],"image":[68],"features":[69],"sequences":[71],"aligning":[73],"them":[74],"with":[75,124,142],"associated":[76],"LiDAR":[77],"point":[78],"clouds.":[79],"is":[82],"intended":[83],"conduct":[85],"editing":[87],"process":[88],"within":[89],"a":[90,101,112,120],"space,":[92],"allowing":[93],"for":[94,145],"manipulation.":[97],"Additionally,":[98],"introduce":[100],"renderer":[104],"project":[106],"edited":[108],"onto":[111,119],"specified":[113],"camera":[114],"plane":[115],"render":[117],"it":[118,127],"2D":[121],"image.":[122],"Combined":[123],"reconstruction,":[126],"overcomes":[128],"challenges":[130],"stemming":[131],"2D/3D":[133],"inconsistencies,":[134],"enabling":[135],"generation":[137],"augmented":[140],"images":[141],"corresponding":[143],"labels":[144],"model":[146],"training.":[147],"validate":[149],"proposed":[151],"method,":[152],"apply":[154],"our":[155],"method":[156],"various":[158],"multi-camera":[159],"detectors,":[162],"consistently":[163],"boosting":[164],"performance.":[166]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}