{"id":"https://openalex.org/W7125901939","doi":"https://doi.org/10.1109/tcsvt.2026.3658133","title":"Revisiting Monocular 3D Object Detection With Depth Thickness Field","display_name":"Revisiting Monocular 3D Object Detection With Depth Thickness Field","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7125901939","doi":"https://doi.org/10.1109/tcsvt.2026.3658133"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3658133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3658133","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Qiude Zhang","orcid":"https://orcid.org/0009-0007-3000-1409"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiude Zhang","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-3000-1409","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122925077","display_name":"Chunyu Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyu Lin","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2847-0349","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhijie Shen","orcid":"https://orcid.org/0000-0002-0037-8084"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Shen","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0037-8084","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047964558","display_name":"Lang Nie","orcid":"https://orcid.org/0000-0002-7776-889X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lang Nie","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7776-889X","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124079315","display_name":"Yao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8581-9554","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09227138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"6","first_page":"7457","last_page":"7470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.5583999752998352,"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":0.5583999752998352,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.12770000100135803,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.10459999740123749,"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/monocular","display_name":"Monocular","score":0.8223000168800354},{"id":"https://openalex.org/keywords/depth-perception","display_name":"Depth perception","score":0.6078000068664551},{"id":"https://openalex.org/keywords/depth-of-field","display_name":"Depth of field","score":0.6019999980926514},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6010000109672546},{"id":"https://openalex.org/keywords/depth-map","display_name":"Depth map","score":0.5742999911308289},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4226999878883362},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.3874000012874603},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.36500000953674316},{"id":"https://openalex.org/keywords/2d-to-3d-conversion","display_name":"2D to 3D conversion","score":0.3619000017642975},{"id":"https://openalex.org/keywords/field-of-view","display_name":"Field of view","score":0.3515999913215637}],"concepts":[{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.8223000168800354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7578999996185303},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7573000192642212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.677299976348877},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.6078000068664551},{"id":"https://openalex.org/C183072630","wikidata":"https://www.wikidata.org/wiki/Q215932","display_name":"Depth of field","level":2,"score":0.6019999980926514},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6010000109672546},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.5742999911308289},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.3874000012874603},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C84824328","wikidata":"https://www.wikidata.org/wiki/Q4633097","display_name":"2D to 3D conversion","level":3,"score":0.3619000017642975},{"id":"https://openalex.org/C150627866","wikidata":"https://www.wikidata.org/wiki/Q1076893","display_name":"Field of view","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C2780575108","wikidata":"https://www.wikidata.org/wiki/Q7316652","display_name":"Retargeting","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C48983235","wikidata":"https://www.wikidata.org/wiki/Q593161","display_name":"Light field","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C157498722","wikidata":"https://www.wikidata.org/wiki/Q34929","display_name":"Three-dimensional space","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C1223959","wikidata":"https://www.wikidata.org/wiki/Q1191960","display_name":"Stereo display","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C23746413","wikidata":"https://www.wikidata.org/wiki/Q1141379","display_name":"Seam carving","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C193581530","wikidata":"https://www.wikidata.org/wiki/Q683778","display_name":"Structured light","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2605000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3658133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3658133","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6248951615","display_name":null,"funder_award_id":"62573039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7296160566","display_name":null,"funder_award_id":"U2441242","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8522156569","display_name":null,"funder_award_id":"U2441242,62172032","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2897529137","https://openalex.org/W2954174912","https://openalex.org/W2963323244","https://openalex.org/W2963351448","https://openalex.org/W2963619659","https://openalex.org/W2963809933","https://openalex.org/W2985775862","https://openalex.org/W3034314779","https://openalex.org/W3035180028","https://openalex.org/W3109395584","https://openalex.org/W3136408985","https://openalex.org/W3156216502","https://openalex.org/W3173668541","https://openalex.org/W3204439495","https://openalex.org/W4200629618","https://openalex.org/W4213402071","https://openalex.org/W4214558638","https://openalex.org/W4312461898","https://openalex.org/W4312713480","https://openalex.org/W4312865155","https://openalex.org/W4313059105","https://openalex.org/W4313169545","https://openalex.org/W4382464460","https://openalex.org/W4383066343","https://openalex.org/W4386066137","https://openalex.org/W4390871919","https://openalex.org/W4390872581","https://openalex.org/W4390873008","https://openalex.org/W4390873354","https://openalex.org/W4393154112","https://openalex.org/W4396941548","https://openalex.org/W4399563629","https://openalex.org/W4400771068","https://openalex.org/W4401415770","https://openalex.org/W4402704555","https://openalex.org/W4402754144","https://openalex.org/W4402754236","https://openalex.org/W4404002786","https://openalex.org/W4404101320","https://openalex.org/W4405303790","https://openalex.org/W4405717395","https://openalex.org/W4405784873","https://openalex.org/W4405838400","https://openalex.org/W4406046958","https://openalex.org/W4411336749","https://openalex.org/W4413146113","https://openalex.org/W4413147166","https://openalex.org/W4415798895","https://openalex.org/W7133243441"],"related_works":[],"abstract_inverted_index":{"Monocular":[0],"3D":[1,41,56,85,129,144],"object":[2,42],"detection":[3,43,155],"is":[4,23],"challenging":[5],"due":[6],"to":[7,82,118,168],"the":[8,27,45,54,88,119,125,134,138,143,148,160,174],"lack":[9],"of":[10,30,59,87,128,140,147],"accurate":[11],"depth.":[12],"However,":[13],"existing":[14,60,169],"depth-assisted":[15],"solutions":[16],"still":[17],"exhibit":[18],"inferior":[19],"performance,":[20],"whose":[21],"reason":[22],"universally":[24],"acknowledged":[25],"as":[26,53],"unsatisfactory":[28],"accuracy":[29],"monocular":[31,40],"depth":[32,46,61,64,68,116,121,149,180],"estimation":[33,181],"models.":[34,182],"In":[35],"this":[36,72],"paper,":[37],"we":[38,74,91],"revisit":[39],"from":[44],"perspective":[47],"and":[48,105,152,162,173],"formulate":[49],"an":[50,106],"additional":[51],"issue":[52],"limited":[55],"structure-aware":[57],"capability":[58,146],"representations":[62,117],"(e.g.,":[63],"one-hot":[65],"encoding":[66],"or":[67],"distribution).":[69],"To":[70],"address":[71],"issue,":[73],"introduce":[75],"a":[76,94,99],"novel":[77],"Depth":[78,101],"Thickness":[79],"Field":[80],"approach":[81],"embed":[83],"clear":[84],"structures":[86],"scenes.":[89],"Specifically,":[90],"present":[92],"MonoDTF,":[93],"scene-to-instance":[95],"depth-adapted":[96],"network":[97],"comprising":[98],"Scene-Level":[100],"Retargeting":[102],"(SDR)":[103],"module":[104],"Instance-Level":[107],"Spatial":[108],"Refinement":[109],"(ISR)":[110],"module.":[111],"The":[112,131,183],"former":[113],"retargets":[114],"traditional":[115],"proposed":[120],"thickness":[122,150],"field,":[123],"incorporating":[124],"scene-level":[126],"perception":[127],"structures.":[130],"latter":[132],"refines":[133],"voxel":[135],"space":[136],"with":[137,178],"guidance":[139],"instances,":[141],"enhancing":[142],"instance-aware":[145],"field":[151],"thus":[153],"improving":[154],"accuracy.":[156],"Extensive":[157],"experiments":[158],"on":[159],"KITTI":[161],"Waymo":[163],"datasets":[164],"demonstrate":[165],"our":[166],"superiority":[167],"state-of-the-art":[170],"(SoTA)":[171],"methods":[172],"universality":[175],"when":[176],"equipped":[177],"different":[179],"source":[184],"codes":[185],"are":[186],"available":[187],"at":[188],"https://github.com/QiuDeZhang/MonoDTF.":[189]},"counts_by_year":[],"updated_date":"2026-06-07T06:13:29.825681","created_date":"2026-01-29T00:00:00"}