{"id":"https://openalex.org/W4390968631","doi":"https://doi.org/10.1109/tip.2024.3352808","title":"Divide and Conquer: Improving Multi-Camera 3D Perception With 2D Semantic-Depth Priors and Input-Dependent Queries","display_name":"Divide and Conquer: Improving Multi-Camera 3D Perception With 2D Semantic-Depth Priors and Input-Dependent Queries","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390968631","doi":"https://doi.org/10.1109/tip.2024.3352808","pmid":"https://pubmed.ncbi.nlm.nih.gov/38236678"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3352808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3352808","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5050250002","display_name":"Qi Song","orcid":"https://orcid.org/0000-0002-5362-4103"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Song","raw_affiliation_strings":["School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036921959","display_name":"Qingyong Hu","orcid":"https://orcid.org/0000-0003-0337-9207"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qingyong Hu","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxford, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458261","display_name":"Chi Zhang","orcid":"https://orcid.org/0009-0000-7773-9338"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102007341","display_name":"Yongquan Chen","orcid":"https://orcid.org/0000-0003-2493-6033"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongquan Chen","raw_affiliation_strings":["School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029499523","display_name":"Rui Huang","orcid":"https://orcid.org/0000-0002-7950-1662"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Huang","raw_affiliation_strings":["School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050250002"],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":3.0245,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.89754114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"33","issue":null,"first_page":"897","last_page":"909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9997000098228455,"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":0.77461838722229},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.719530463218689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7008650302886963},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5636477470397949},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5515854954719543},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5470046997070312},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5424443483352661},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.49921083450317383},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49398332834243774},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4240490794181824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40216028690338135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4005950093269348},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.1880989968776703}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77461838722229},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.719530463218689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7008650302886963},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5636477470397949},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5515854954719543},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5470046997070312},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5424443483352661},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.49921083450317383},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49398332834243774},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4240490794181824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40216028690338135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4005950093269348},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.1880989968776703},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3352808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3352808","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:38236678","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38236678","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3177370927","display_name":null,"funder_award_id":"ZDSYS20211021111415025","funder_id":"https://openalex.org/F4320336569","funder_display_name":"Shenzhen Science and Technology Innovation Program"},{"id":"https://openalex.org/G7367449780","display_name":null,"funder_award_id":"JCYJ20220818103006012","funder_id":"https://openalex.org/F4320336569","funder_display_name":"Shenzhen Science and Technology Innovation Program"}],"funders":[{"id":"https://openalex.org/F4320336569","display_name":"Shenzhen Science and Technology Innovation Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1905829557","https://openalex.org/W1966151866","https://openalex.org/W2150839555","https://openalex.org/W2302255633","https://openalex.org/W2520707372","https://openalex.org/W2560023338","https://openalex.org/W2798405286","https://openalex.org/W2890003176","https://openalex.org/W2902824710","https://openalex.org/W2908510526","https://openalex.org/W2948515602","https://openalex.org/W2962850830","https://openalex.org/W2963263347","https://openalex.org/W2963351448","https://openalex.org/W2963488291","https://openalex.org/W2964294967","https://openalex.org/W2967324759","https://openalex.org/W2969987486","https://openalex.org/W2985775862","https://openalex.org/W3010003086","https://openalex.org/W3010707748","https://openalex.org/W3034669477","https://openalex.org/W3034868890","https://openalex.org/W3035049382","https://openalex.org/W3035574168","https://openalex.org/W3036452913","https://openalex.org/W3087549734","https://openalex.org/W3096609285","https://openalex.org/W3100744475","https://openalex.org/W3102343027","https://openalex.org/W3109395584","https://openalex.org/W3136714643","https://openalex.org/W3172084025","https://openalex.org/W3173668541","https://openalex.org/W3173727695","https://openalex.org/W3193266637","https://openalex.org/W3203158837","https://openalex.org/W3205150709","https://openalex.org/W3215100485","https://openalex.org/W3215957616","https://openalex.org/W4214530037","https://openalex.org/W4214558638","https://openalex.org/W4220989862","https://openalex.org/W4224259431","https://openalex.org/W4225343834","https://openalex.org/W4225793049","https://openalex.org/W4226040545","https://openalex.org/W4226305814","https://openalex.org/W4226342918","https://openalex.org/W4281255813","https://openalex.org/W4285606661","https://openalex.org/W4297899592","https://openalex.org/W4303443326","https://openalex.org/W4304098216","https://openalex.org/W4312641958","https://openalex.org/W4312894406","https://openalex.org/W4312903731","https://openalex.org/W4312954223","https://openalex.org/W4313072575","https://openalex.org/W4318907301","https://openalex.org/W4319300075","https://openalex.org/W4376481110","https://openalex.org/W4382240316","https://openalex.org/W4382464460","https://openalex.org/W4386072002","https://openalex.org/W6726497184","https://openalex.org/W6739901393","https://openalex.org/W6756392615","https://openalex.org/W6757817989","https://openalex.org/W6760424586","https://openalex.org/W6767379092","https://openalex.org/W6780075094","https://openalex.org/W6783292247","https://openalex.org/W6799331316","https://openalex.org/W6800899058","https://openalex.org/W6802311648","https://openalex.org/W6810240388","https://openalex.org/W6811230113","https://openalex.org/W6838844109","https://openalex.org/W6843796254","https://openalex.org/W6845491643","https://openalex.org/W6846396092","https://openalex.org/W6849396345","https://openalex.org/W6880983126"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2023946029"],"abstract_inverted_index":{"3D":[0,5,29,162],"perception":[1],"tasks,":[2],"such":[3],"as":[4,89],"object":[6,115,163],"detection":[7,164],"and":[8,28,46,55,87,106,117,150,165],"Bird's-Eye-View":[9],"(BEV)":[10],"segmentation":[11,167],"using":[12],"multi-camera":[13],"images,":[14],"have":[15],"drawn":[16],"significant":[17],"attention":[18],"recently.":[19],"Despite":[20],"the":[21,41,51,60,68,96,111,129,133,137,148,154],"fact":[22],"that":[23,84,102,127],"accurately":[24],"estimating":[25],"both":[26,161],"semantic":[27,45,105,130],"scene":[30],"layouts":[31],"are":[32],"crucial":[33],"for":[34],"this":[35],"task,":[36],"existing":[37],"techniques":[38],"often":[39],"neglect":[40],"synergistic":[42],"effects":[43],"of":[44,53,63,71,98,114,136,157],"depth":[47,107],"cues,":[48],"leading":[49],"to":[50],"occurrence":[52],"classification":[54],"position":[56,118],"estimation":[57],"errors.":[58],"Additionally,":[59],"input-independent":[61],"nature":[62],"initial":[64,134],"queries":[65,135],"also":[66],"limits":[67],"learning":[69,112],"capacity":[70],"Transformer-based":[72],"models.":[73],"To":[74],"tackle":[75],"these":[76],"challenges,":[77],"we":[78,121],"propose":[79],"an":[80,99],"input-aware":[81,143],"Transformer":[82],"framework":[83],"leverages":[85],"Semantics":[86],"Depth":[88],"priors":[90],"(named":[91],"SDTR).":[92],"Our":[93],"approach":[94],"involves":[95],"use":[97],"S-D":[100],"Encoder":[101],"explicitly":[103],"models":[104],"priors,":[108],"thereby":[109],"disentangling":[110],"process":[113],"categorization":[116],"estimation.":[119],"Moreover,":[120],"introduce":[122],"a":[123],"Prior-guided":[124],"Query":[125],"Builder":[126],"incorporates":[128],"prior":[131],"into":[132],"Transformer,":[138],"resulting":[139],"in":[140,160],"more":[141],"effective":[142],"queries.":[144],"Extensive":[145],"experiments":[146],"on":[147],"nuScenes":[149],"Lyft":[151],"benchmarks":[152],"demonstrate":[153],"state-of-the-art":[155],"performance":[156],"our":[158],"method":[159],"BEV":[166],"tasks.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}