{"id":"https://openalex.org/W4383108623","doi":"https://doi.org/10.1109/icra48891.2023.10160483","title":"Depth Is All You Need for Monocular 3D Detection","display_name":"Depth Is All You Need for Monocular 3D Detection","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108623","doi":"https://doi.org/10.1109/icra48891.2023.10160483"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5031093078","display_name":"Dennis Park","orcid":null},"institutions":[{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]}],"countries":[],"is_corresponding":true,"raw_author_name":"Dennis Park","raw_affiliation_strings":["Toyota Research Institute"],"affiliations":[{"raw_affiliation_string":"Toyota Research Institute","institution_ids":["https://openalex.org/I4391768151"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092397663","display_name":"Jie Li","orcid":"https://orcid.org/0009-0006-2835-6780"},"institutions":[{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Toyota Research Institute"],"affiliations":[{"raw_affiliation_string":"Toyota Research Institute","institution_ids":["https://openalex.org/I4391768151"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080500782","display_name":"Dian Chen","orcid":"https://orcid.org/0000-0002-5502-6254"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dian Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063755961","display_name":"Vitor Guizilini","orcid":"https://orcid.org/0000-0002-8715-8307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vitor Guizilini","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075018873","display_name":"Adrien Gaidon","orcid":"https://orcid.org/0000-0001-8820-550X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adrien Gaidon","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5031093078"],"corresponding_institution_ids":["https://openalex.org/I4391768151"],"apc_list":null,"apc_paid":null,"fwci":0.8597,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75132212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7024","last_page":"7031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9998999834060669,"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":0.9998999834060669,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9944999814033508,"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":0.8316084146499634},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8064371943473816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.724862813949585},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.7181088924407959},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6849694848060608},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5244103670120239},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4846556782722473},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4279455244541168},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4146062731742859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8316084146499634},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8064371943473816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.724862813949585},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7181088924407959},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6849694848060608},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5244103670120239},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4846556782722473},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4279455244541168},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4146062731742859},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2133665775","https://openalex.org/W2150066425","https://openalex.org/W2397830550","https://openalex.org/W2565639579","https://openalex.org/W2605189827","https://openalex.org/W2609883120","https://openalex.org/W2781228439","https://openalex.org/W2951234442","https://openalex.org/W2953941229","https://openalex.org/W2954174912","https://openalex.org/W2963171573","https://openalex.org/W2963488291","https://openalex.org/W2963557767","https://openalex.org/W2968296999","https://openalex.org/W2972211064","https://openalex.org/W2981857055","https://openalex.org/W2982770724","https://openalex.org/W2985775862","https://openalex.org/W2989963265","https://openalex.org/W2996166203","https://openalex.org/W2997790735","https://openalex.org/W2998633559","https://openalex.org/W3011371059","https://openalex.org/W3034479628","https://openalex.org/W3034604951","https://openalex.org/W3034975685","https://openalex.org/W3035049382","https://openalex.org/W3035172746","https://openalex.org/W3035180028","https://openalex.org/W3035254347","https://openalex.org/W3035574168","https://openalex.org/W3035749845","https://openalex.org/W3087402140","https://openalex.org/W3096609285","https://openalex.org/W3106834807","https://openalex.org/W3109240920","https://openalex.org/W3113085706","https://openalex.org/W3173668541","https://openalex.org/W3176319743","https://openalex.org/W3176821088","https://openalex.org/W3180720907","https://openalex.org/W3183579734","https://openalex.org/W3204439495","https://openalex.org/W3215100485","https://openalex.org/W4214558638","https://openalex.org/W4221155237","https://openalex.org/W4225793049","https://openalex.org/W4226305814","https://openalex.org/W4288095514","https://openalex.org/W4312713480","https://openalex.org/W4312894406","https://openalex.org/W4313059105","https://openalex.org/W4313153185","https://openalex.org/W6620707391","https://openalex.org/W6685261749","https://openalex.org/W6712616374","https://openalex.org/W6752497527","https://openalex.org/W6760424586","https://openalex.org/W6762004615","https://openalex.org/W6764514022","https://openalex.org/W6769011798","https://openalex.org/W6770923672","https://openalex.org/W6778485988","https://openalex.org/W6781865508","https://openalex.org/W6783359081","https://openalex.org/W6786888487","https://openalex.org/W6791353490","https://openalex.org/W6799331316","https://openalex.org/W6809883588","https://openalex.org/W6811079899","https://openalex.org/W6811230113","https://openalex.org/W6936030810"],"related_works":["https://openalex.org/W200819717","https://openalex.org/W2012531322","https://openalex.org/W2032269556","https://openalex.org/W2944448661","https://openalex.org/W2064421702","https://openalex.org/W1991834176","https://openalex.org/W4253756925","https://openalex.org/W2131956013","https://openalex.org/W2805523177","https://openalex.org/W2785900585"],"abstract_inverted_index":{"A":[0],"key":[1],"contributor":[2],"to":[3,21,96,103],"recent":[4,36],"progress":[5],"in":[6,61,80,129],"3D":[7,54,105],"detection":[8],"from":[9],"single":[10],"images":[11],"is":[12,59,123],"monocular":[13],"depth":[14,23,39,48,74,99,121],"estimation.":[15],"Existing":[16],"methods":[17,85],"focus":[18],"on":[19,153,174],"how":[20],"leverage":[22,38,86],"explicitly,":[24],"by":[25,63,118],"generating":[26,120],"pseudo-pointclouds":[27],"or":[28,90],"providing":[29],"attention":[30],"cues":[31],"for":[32,53],"image":[33],"features.":[34],"More":[35],"works":[37],"prediction":[40],"as":[41],"a":[42],"pretraining":[43],"task":[44],"and":[45,156,169],"fine-tune":[46,97],"the":[47,57,73,77,98,127,133,148,151,160],"representation":[49,75],"while":[50,158],"training":[51,94,117],"it":[52],"detection.":[55],"However,":[56],"adaptation":[58],"limited":[60],"scale":[62],"manual":[64],"labels.":[65],"In":[66],"this":[67],"work,":[68],"we":[69,112],"propose":[70],"further":[71],"aligning":[72],"with":[76],"target":[78],"domain":[79],"an":[81],"unsupervised":[82],"fashion.":[83],"Our":[84],"commonly":[87],"available":[88,173],"LiDAR":[89],"RGB":[91,110],"videos":[92],"during":[93],"time":[95],"representation,":[100],"which":[101],"leads":[102],"improved":[104],"detectors.":[106],"Especially":[107],"when":[108],"using":[109],"videos,":[111],"show":[113],"that":[114],"our":[115,142],"two-stage":[116],"first":[119],"pseudo-labels":[122],"critical,":[124],"because":[125],"of":[126,139,150,163],"inconsistency":[128],"loss":[130],"distribution":[131],"between":[132],"two":[134],"tasks.":[135],"With":[136],"either":[137],"type":[138],"reference":[140],"data,":[141],"multi-task":[143],"learning":[144],"approach":[145],"improves":[146],"over":[147],"state":[149],"art":[152],"both":[154],"KITTI":[155],"NuScenes,":[157],"matching":[159],"test-time":[161],"complexity":[162],"its":[164],"single-task":[165],"sub-network.":[166],"Source":[167],"code":[168],"pretrained":[170],"models":[171],"are":[172],"https://github.com/TRI-ML/DD3D.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}