{"id":"https://openalex.org/W7141752518","doi":"https://doi.org/10.1109/icce67443.2026.11449883","title":"Evaluating Foundational Depth Models for Zero-shot 3D Box Lifting from 2D detections","display_name":"Evaluating Foundational Depth Models for Zero-shot 3D Box Lifting from 2D detections","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7141752518","doi":"https://doi.org/10.1109/icce67443.2026.11449883"},"language":null,"primary_location":{"id":"doi:10.1109/icce67443.2026.11449883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce67443.2026.11449883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Consumer Electronics (ICCE)","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/A5100039184","display_name":"Asmaa loulou","orcid":null},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]},{"id":"https://openalex.org/I4210154947","display_name":"Ford Otosan (Turkey)","ror":"https://ror.org/04h48jk55","country_code":"TR","type":"company","lineage":["https://openalex.org/I4210154947"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Asmaa Loulou","raw_affiliation_strings":["Sabanci University, Ford Otosan,Istanbul,Turkey"],"affiliations":[{"raw_affiliation_string":"Sabanci University, Ford Otosan,Istanbul,Turkey","institution_ids":["https://openalex.org/I134235054","https://openalex.org/I4210154947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049849796","display_name":"Eren Aydemir","orcid":null},"institutions":[{"id":"https://openalex.org/I4210154947","display_name":"Ford Otosan (Turkey)","ror":"https://ror.org/04h48jk55","country_code":"TR","type":"company","lineage":["https://openalex.org/I4210154947"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Eren Aydemir","raw_affiliation_strings":["Ford Otosan,Istanbul,Turkey"],"affiliations":[{"raw_affiliation_string":"Ford Otosan,Istanbul,Turkey","institution_ids":["https://openalex.org/I4210154947"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031429692","display_name":"Mustafa \u00dcnel","orcid":"https://orcid.org/0000-0002-2907-3233"},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mustafa Unel","raw_affiliation_strings":["Sabanci University,Istanbul,Turkey"],"affiliations":[{"raw_affiliation_string":"Sabanci University,Istanbul,Turkey","institution_ids":["https://openalex.org/I134235054"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100039184"],"corresponding_institution_ids":["https://openalex.org/I134235054","https://openalex.org/I4210154947"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.95206817,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.16179999709129333,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.16179999709129333,"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/T10638","display_name":"Optical measurement and interference techniques","score":0.1128000020980835,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.09849999845027924,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28700000047683716},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.28139999508857727},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.24699999392032623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4925999939441681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48260000348091125},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46459999680519104},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2745000123977661},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26010000705718994},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.24699999392032623},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24500000476837158}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce67443.2026.11449883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce67443.2026.11449883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Consumer Electronics (ICCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.4406178593635559,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2468368736","https://openalex.org/W2560544142","https://openalex.org/W2954174912","https://openalex.org/W2955639361","https://openalex.org/W2999947750","https://openalex.org/W3034479628","https://openalex.org/W3172087149","https://openalex.org/W3176319743","https://openalex.org/W4214520160","https://openalex.org/W4367146742","https://openalex.org/W4383109103","https://openalex.org/W4390874575","https://openalex.org/W4402727359"],"related_works":[],"abstract_inverted_index":{"Monocular":[0],"3D":[1,61,102,112,164,184],"object":[2,62],"detection":[3,165],"offers":[4],"a":[5,53,76,82,179,193],"low-cost":[6],"alternative":[7],"to":[8,57,98,195],"LiDAR-based":[9],"perception,":[10],"but":[11,189],"remains":[12],"fundamentally":[13],"limited":[14],"by":[15],"scale":[16],"ambiguity":[17],"and":[18,43,84,94,119,131,151],"the":[19,140,148,197],"absence":[20],"of":[21,127,199],"geometric":[22],"depth":[23,70,96,133,201],"cues":[24],"in":[25,186],"single":[26],"images.":[27],"Although":[28],"recent":[29],"deep":[30],"learning":[31,158],"approaches":[32],"have":[33],"advanced":[34],"performance,":[35],"they":[36],"typically":[37],"rely":[38],"on":[39,147],"large-scale":[40],"annotated":[41],"datasets":[42,118],"complex,":[44],"fully":[45],"supervised":[46],"pipelines.":[47],"In":[48],"this":[49],"work,":[50],"we":[51],"introduce":[52],"benchmarking":[54,137],"framework":[55,146],"designed":[56],"systematically":[58],"evaluate":[59,144],"zero-shot":[60],"lifting":[63],"from":[64],"2D":[65,90,110,129],"detections":[66,100],"using":[67,156],"pre-trained":[68],"monocular":[69,132],"estimation":[71],"models.":[72],"Rather":[73],"than":[74],"proposing":[75],"new":[77],"detector,":[78],"our":[79,145],"tool":[80,181],"provides":[81,178],"modular":[83,122],"training-free":[85],"platform":[86],"that":[87],"combines":[88],"off-the-shelf":[89],"detectors,":[91],"camera":[92],"calibration,":[93],"existing":[95],"models":[97,171,202],"project":[99],"into":[101],"space.":[103],"Our":[104,174],"method":[105],"does":[106],"not":[107,155,176],"require":[108],"labeled":[109],"or":[111,159],"data,":[113],"enabling":[114],"flexible":[115],"deployment":[116],"across":[117],"domains.":[120],"The":[121],"design":[123],"allows":[124],"plug-and-play":[125],"evaluation":[126],"both":[128],"detectors":[130],"models,":[134],"facilitating":[135],"controlled":[136],"without":[138],"retraining":[139],"entire":[141],"model.":[142],"We":[143],"KITTI":[149],"benchmark":[150],"show":[152],"that,":[153],"despite":[154],"any":[157],"fine-tuning,":[160],"it":[161],"achieves":[162],"competitive":[163],"results,":[166],"particularly":[167],"when":[168],"strong":[169],"foundation":[170],"are":[172],"used.":[173],"approach":[175],"only":[177],"practical":[180],"for":[182,203],"rapid":[183],"perception":[185],"label-scarce":[187],"scenarios,":[188],"also":[190],"serves":[191],"as":[192],"baseline":[194],"analyze":[196],"effectiveness":[198],"different":[200],"object-level":[204],"spatial":[205],"reasoning.":[206]},"counts_by_year":[],"updated_date":"2026-03-29T06:01:01.467347","created_date":"2026-03-28T00:00:00"}