{"id":"https://openalex.org/W4295934562","doi":"https://doi.org/10.1109/tcsvt.2022.3207105","title":"MonoIndoor++: Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments","display_name":"MonoIndoor++: Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments","publication_year":2022,"publication_date":"2022-09-15","ids":{"openalex":"https://openalex.org/W4295934562","doi":"https://doi.org/10.1109/tcsvt.2022.3207105"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3207105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3207105","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":"https://openalex.org/A5017810813","display_name":"Runze Li","orcid":"https://orcid.org/0000-0001-9153-5796"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Runze Li","raw_affiliation_strings":["Department of Computer Science, University of California at Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9153-5796","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California at Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063587709","display_name":"Pan Ji","orcid":"https://orcid.org/0000-0001-6213-554X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Ji","raw_affiliation_strings":["OPPO US Research Center, InnoPeak Technology Inc., Palo Alto, CA, USA","XR Vision Labs, Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO US Research Center, InnoPeak Technology Inc., Palo Alto, CA, USA","institution_ids":[]},{"raw_affiliation_string":"XR Vision Labs, Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018343158","display_name":"Yi Xu","orcid":"https://orcid.org/0000-0003-2126-6054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Xu","raw_affiliation_strings":["OPPO US Research Center, InnoPeak Technology Inc., Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2126-6054","affiliations":[{"raw_affiliation_string":"OPPO US Research Center, InnoPeak Technology Inc., Palo Alto, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071522801","display_name":"Bir Bhanu","orcid":"https://orcid.org/0000-0001-8971-6416"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bir Bhanu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California at Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8971-6416","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California at Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1943,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.89177653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"33","issue":"2","first_page":"830","last_page":"846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":1.0,"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":1.0,"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":0.9973999857902527,"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":0.9965000152587891,"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":0.7334583401679993},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.7078655958175659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6940773725509644},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6464859247207642},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5286182761192322},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4950820505619049},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.42188113927841187},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4167148172855377},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12102103233337402},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08011692762374878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7334583401679993},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7078655958175659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6940773725509644},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6464859247207642},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5286182761192322},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4950820505619049},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.42188113927841187},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4167148172855377},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12102103233337402},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08011692762374878},{"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/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3207105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3207105","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":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1905829557","https://openalex.org/W1915250530","https://openalex.org/W1989476314","https://openalex.org/W1992178727","https://openalex.org/W2074254947","https://openalex.org/W2083047701","https://openalex.org/W2108598243","https://openalex.org/W2124907686","https://openalex.org/W2125416623","https://openalex.org/W2132947399","https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2300779272","https://openalex.org/W2396274919","https://openalex.org/W2436453945","https://openalex.org/W2471962767","https://openalex.org/W2519683295","https://openalex.org/W2520707372","https://openalex.org/W2535547924","https://openalex.org/W2561074213","https://openalex.org/W2594519801","https://openalex.org/W2609883120","https://openalex.org/W2886322387","https://openalex.org/W2890949887","https://openalex.org/W2935854115","https://openalex.org/W2942368658","https://openalex.org/W2955639361","https://openalex.org/W2962456457","https://openalex.org/W2962741876","https://openalex.org/W2962807621","https://openalex.org/W2963091558","https://openalex.org/W2963488291","https://openalex.org/W2963583471","https://openalex.org/W2963591054","https://openalex.org/W2963619659","https://openalex.org/W2963654727","https://openalex.org/W2963760790","https://openalex.org/W2964189516","https://openalex.org/W2981413347","https://openalex.org/W2985775862","https://openalex.org/W2990394353","https://openalex.org/W2990946490","https://openalex.org/W3009257710","https://openalex.org/W3034364596","https://openalex.org/W3081167590","https://openalex.org/W3091687063","https://openalex.org/W3102327032","https://openalex.org/W3108735274","https://openalex.org/W3108746553","https://openalex.org/W3109585842","https://openalex.org/W3118453581","https://openalex.org/W3138516171","https://openalex.org/W3145609993","https://openalex.org/W3162552392","https://openalex.org/W3172610252","https://openalex.org/W3173727695","https://openalex.org/W3175682855","https://openalex.org/W3202016623","https://openalex.org/W4200495456","https://openalex.org/W4214520160","https://openalex.org/W4214731463","https://openalex.org/W4312280420","https://openalex.org/W4312349930","https://openalex.org/W6618372016","https://openalex.org/W6620707391","https://openalex.org/W6685261749","https://openalex.org/W6712702053","https://openalex.org/W6739778489","https://openalex.org/W6739901393","https://openalex.org/W6753441378","https://openalex.org/W6756774061","https://openalex.org/W6763422710","https://openalex.org/W6763530150","https://openalex.org/W6766978945","https://openalex.org/W6767088534","https://openalex.org/W6779994873","https://openalex.org/W6780775866","https://openalex.org/W6791097704","https://openalex.org/W6800540912"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W2123263858","https://openalex.org/W2788972299","https://openalex.org/W3127959533","https://openalex.org/W2521347458","https://openalex.org/W2498789492","https://openalex.org/W3034529322","https://openalex.org/W2729981612","https://openalex.org/W4307623796"],"abstract_inverted_index":{"Self-supervised":[0],"monocular":[1,48,179],"depth":[2,20,46,63,80,85,180,187,201,214],"estimation":[3,181,223,236,257],"has":[4],"seen":[5],"significant":[6],"progress":[7],"in":[8,12,26,57,93,226],"recent":[9],"years,":[10],"especially":[11,143],"outdoor":[13,43,94,138],"environments,":[14,44,52],"i.e.,":[15,285],"autonomous":[16],"driving":[17,146],"scenes.":[18],"However,":[19],"prediction":[21],"results":[22,56],"are":[23,35,140],"not":[24],"satisfying":[25],"indoor":[27,51,66,109,183,283],"scenes":[28,95],"where":[29],"most":[30],"of":[31,47,65,137,170,177,281,300,317],"the":[32,62,79,90,98,101,105,108,125,135,175,206,212,268,293,298,312],"existing":[33],"data":[34],"captured":[36],"with":[37,112,190],"hand-held":[38],"devices.":[39],"As":[40],"compared":[41],"to":[42,82,128,163,197,231,238,248,261,270],"estimating":[45],"videos":[49],"for":[50,78,87,124,144,173,182,253],"using":[53,219],"self-supervised":[54,178],"methods,":[55,228],"two":[58],"additional":[59],"challenges:":[60],"(i)":[61],"range":[64],"video":[67],"sequences":[68,110,139],"varies":[69],"a":[70,156,168,186,199,220,233,279,306],"lot":[71],"across":[72,243],"different":[73],"frames,":[74],"making":[75],"it":[76],"difficult":[77],"network":[81,127,194],"induce":[83],"consistent":[84],"cues":[86],"training,":[88],"whereas":[89],"maximum":[91,213],"distance":[92],"mostly":[96],"stays":[97],"same":[99],"as":[100,149,225],"camera":[102,132,241],"usually":[103],"sees":[104],"sky;":[106],"(ii)":[107],"recorded":[111],"handheld":[113],"devices":[114],"often":[115],"contain":[116],"much":[117],"more":[118],"rotational":[119],"motions,":[120],"which":[121],"cause":[122],"difficulties":[123],"pose":[126,222,235,256,271],"predict":[129],"accurate":[130],"relative":[131,240],"poses,":[133],"while":[134],"motions":[136],"pre-dominantly":[141],"translational,":[142],"street-scene":[145],"datasets":[147],"such":[148],"KITTI.":[150],"In":[151,296],"this":[152],"work,":[153],"we":[154,229,259],"propose":[155,230,260],"novel":[157],"framework-MonoIndoor++":[158],"by":[159],"giving":[160],"special":[161],"considerations":[162],"those":[164],"challenges":[165],"and":[166,205,290,311,315,327],"consolidating":[167],"set":[169],"good":[171,313],"practices":[172],"improving":[174],"performance":[176],"environments.":[184],"First,":[185],"factorization":[188],"module":[189,237,302],"transformer-based":[191],"scale":[192,202,208],"regression":[193],"is":[195,276,303,321],"proposed":[196,274],"estimate":[198,239],"global":[200],"factor":[203,209],"explicitly,":[204],"predicted":[207],"can":[210],"indicate":[211],"values.":[215],"Second,":[216],"rather":[217],"than":[218],"single-stage":[221],"strategy":[224],"previous":[227],"utilize":[232],"residual":[234,255],"poses":[242],"consecutive":[244],"frames":[245],"iteratively.":[246],"Third,":[247],"incorporate":[249],"extensive":[250],"coordinates":[251],"guidance":[252],"our":[254,318],"module,":[258],"perform":[262],"coordinate":[263],"convolutional":[264],"encoding":[265],"directly":[266],"over":[267],"inputs":[269],"networks.":[272],"The":[273],"method":[275],"validated":[277],"on":[278,325],"variety":[280],"benchmark":[282],"datasets,":[284],"EuRoC":[286],"MAV,":[287],"NYUv2,":[288],"ScanNet":[289,326],"7-Scenes,":[291],"demonstrating":[292],"state-of-the-art":[294],"performance.":[295],"addition,":[297],"effectiveness":[299],"each":[301],"shown":[304],"through":[305],"carefully":[307],"conducted":[308],"ablation":[309],"study":[310],"generalization":[314],"universality":[316],"trained":[319],"model":[320],"also":[322],"demonstrated,":[323],"specifically":[324],"7-Scenes":[328],"datasets.":[329]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":12}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}