{"id":"https://openalex.org/W4313040116","doi":"https://doi.org/10.1109/tmm.2022.3224810","title":"Towards Comprehensive Monocular Depth Estimation: Multiple Heads are Better Than One","display_name":"Towards Comprehensive Monocular Depth Estimation: Multiple Heads are Better Than One","publication_year":2022,"publication_date":"2022-11-25","ids":{"openalex":"https://openalex.org/W4313040116","doi":"https://doi.org/10.1109/tmm.2022.3224810"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3224810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3224810","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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":"https://openalex.org/A5000411800","display_name":"Shuwei Shao","orcid":"https://orcid.org/0000-0001-8057-1599"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuwei Shao","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","Hangzhou Innovation Institute, Beihang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8057-1599","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428066","display_name":"Ran Li","orcid":"https://orcid.org/0000-0002-0487-1570"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Li","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","Hangzhou Innovation Institute, Beihang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0487-1570","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076604839","display_name":"Zhongcai Pei","orcid":"https://orcid.org/0000-0001-7748-8591"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongcai Pei","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","Hangzhou Innovation Institute, Beihang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7748-8591","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376861","display_name":"Zhong Liu","orcid":"https://orcid.org/0000-0003-3242-5997"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Liu","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","Hangzhou Innovation Institute, Beihang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3242-5997","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026365889","display_name":"Weihai Chen","orcid":"https://orcid.org/0000-0001-7912-4505"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihai Chen","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","Hangzhou Innovation Institute, Beihang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7912-4505","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101615234","display_name":"Wentao Zhu","orcid":"https://orcid.org/0000-0002-7505-9512"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wentao Zhu","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7505-9512","affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374736","display_name":"Xingming Wu","orcid":"https://orcid.org/0000-0002-4334-0465"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingming Wu","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","Hangzhou Innovation Institute, Beihang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4334-0465","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015525872","display_name":"Baochang Zhang","orcid":"https://orcid.org/0000-0001-7396-6218"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baochang Zhang","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","Hangzhou Innovation Institute, Beihang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7396-6218","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4368,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.90558988,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"7660","last_page":"7671"},"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/T10638","display_name":"Optical measurement and interference techniques","score":0.9991999864578247,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7995429039001465},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.6005290746688843},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5815894603729248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.532997727394104},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4886165261268616},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.35111159086227417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995429039001465},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.6005290746688843},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5815894603729248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.532997727394104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4886165261268616},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.35111159086227417},{"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/tmm.2022.3224810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3224810","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1318288144","display_name":null,"funder_award_id":"62076016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2114630501","display_name":null,"funder_award_id":"2020C01109","funder_id":"https://openalex.org/F8142712028","funder_display_name":"Key Research and Development Program of Zhejiang Province"},{"id":"https://openalex.org/G2312352739","display_name":null,"funder_award_id":"L223024","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G558676831","display_name":null,"funder_award_id":"61620106012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6206016144","display_name":null,"funder_award_id":"0022/2019/AKP","funder_id":"https://openalex.org/F4320323893","funder_display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia"},{"id":"https://openalex.org/G6252892545","display_name":null,"funder_award_id":"61573048","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"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320323893","display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia","ror":"https://ror.org/05vna4324"},{"id":"https://openalex.org/F8142712028","display_name":"Key Research and Development Program of Zhejiang Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1905829557","https://openalex.org/W1923184257","https://openalex.org/W2100128988","https://openalex.org/W2106390255","https://openalex.org/W2115579991","https://openalex.org/W2117539524","https://openalex.org/W2152761983","https://openalex.org/W2194775991","https://openalex.org/W2412782625","https://openalex.org/W2549139847","https://openalex.org/W2587989515","https://openalex.org/W2620998106","https://openalex.org/W2774018344","https://openalex.org/W2795321555","https://openalex.org/W2798927139","https://openalex.org/W2941243189","https://openalex.org/W2962741876","https://openalex.org/W2962807621","https://openalex.org/W2962960377","https://openalex.org/W2963285578","https://openalex.org/W2963446712","https://openalex.org/W2963488291","https://openalex.org/W2963591054","https://openalex.org/W2970602317","https://openalex.org/W2974576232","https://openalex.org/W2990946490","https://openalex.org/W3047871852","https://openalex.org/W3094502228","https://openalex.org/W3098341014","https://openalex.org/W3108179104","https://openalex.org/W3112819693","https://openalex.org/W3118273996","https://openalex.org/W3127743092","https://openalex.org/W3138516171","https://openalex.org/W3142837074","https://openalex.org/W3160694286","https://openalex.org/W3173409262","https://openalex.org/W3188511781","https://openalex.org/W4200072305","https://openalex.org/W4214520160","https://openalex.org/W4214651109","https://openalex.org/W4295308583","https://openalex.org/W4312460030","https://openalex.org/W6683067110","https://openalex.org/W6685261749","https://openalex.org/W6685562342","https://openalex.org/W6730042731","https://openalex.org/W6737496325","https://openalex.org/W6739901393","https://openalex.org/W6756040250","https://openalex.org/W6757817989","https://openalex.org/W6766261854","https://openalex.org/W6780651745","https://openalex.org/W6783873723","https://openalex.org/W6784333009","https://openalex.org/W6790703111"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Depth":[0],"estimation":[1,196],"attracts":[2],"widespread":[3],"attention":[4],"in":[5,37,43],"the":[6,57,63,120,125,133,180,190,194,211,218,224,232],"computer":[7],"vision":[8],"community.":[9],"However,":[10],"it":[11],"is":[12,79],"still":[13],"quite":[14],"difficult":[15],"to":[16,35,61,70,119,132,142,152,173,223],"recover":[17],"an":[18],"accurate":[19,75],"depth":[20,68,76,94,137,146,165,176,195],"map":[21],"using":[22],"only":[23],"one":[24],"RGB":[25],"image.":[26],"We":[27],"observe":[28],"a":[29,72,144,163],"phenomenon":[30,58],"that":[31,199],"existing":[32],"methods":[33],"tend":[34],"fail":[36],"different":[38,98],"cases,":[39],"caused":[40],"by":[41,96,116],"differences":[42],"network":[44,103],"architecture,":[45],"loss":[46],"function":[47],"and":[48,59,74,100,129,158,183,197,231],"so":[49],"on.":[50],"In":[51],"this":[52],"work,":[53],"we":[54,89,149,171,186,215],"investigate":[55],"into":[56,162],"propose":[60],"integrate":[62],"strengths":[64],"of":[65,127,135],"multiple":[66,91,155],"weak":[67,156],"predictor":[69],"build":[71],"comprehensive":[73,145],"predictor,":[77],"which":[78,139,170],"critical":[80],"for":[81],"many":[82],"real-world":[83],"applications,":[84],"e.g.,":[85],"3D":[86],"reconstruction.":[87],"Specifically,":[88],"construct":[90],"base":[92],"(weak)":[93],"predictors":[95],"utilizing":[97],"Transformer-based":[99],"convolutional":[101],"neural":[102,191],"(CNN)-based":[104],"architectures.":[105],"Transformer":[106,117,128],"establishes":[107],"long-range":[108],"correlation":[109],"while":[110],"CNN":[111,130],"preserves":[112],"local":[113],"information":[114],"ignored":[115],"due":[118],"spatial":[121],"inductive":[122],"bias.":[123],"Therefore,":[124],"coupling":[126],"contributes":[131],"generation":[134],"complementary":[136],"estimates,":[138],"are":[140],"essential":[141],"achieve":[143],"predictor.":[147],"Then,":[148],"design":[150],"mixers":[151],"learn":[153],"from":[154],"predictions":[157],"adaptively":[159],"fuse":[160],"them":[161],"strong":[164,237],"estimate.":[166],"The":[167],"resultant":[168],"model,":[169],"refer":[172],"as":[174],"Transformer-assisted":[175],"ensembles":[177,192],"(TEDepth).":[178],"On":[179],"standard":[181],"NYU-Depth-v2":[182,222],"KITTI":[184],"datasets,":[185],"thoroughly":[187],"explore":[188],"how":[189],"affect":[193],"demonstrate":[198],"our":[200],"TEDepth":[201],"achieves":[202],"better":[203],"results":[204,234],"than":[205],"previous":[206],"state-of-the-art":[207],"approaches.":[208],"To":[209],"validate":[210],"generalizability":[212],"across":[213],"cameras,":[214],"directly":[216],"apply":[217],"models":[219],"trained":[220],"on":[221],"SUN":[225],"RGB-D":[226],"dataset":[227],"without":[228],"any":[229],"fine-tuning,":[230],"superior":[233],"emphasize":[235],"its":[236],"generalizability.":[238]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}