{"id":"https://openalex.org/W6910265055","doi":"https://doi.org/10.4233/uuid:d0f89fb8-bb07-499d-bff4-29b074ed17ef","title":"Data-efficient learning of geometric structures from single-view images","display_name":"Data-efficient learning of geometric structures from single-view images","publication_year":2022,"publication_date":"2022-04-01","ids":{"openalex":"https://openalex.org/W6910265055","doi":"https://doi.org/10.4233/uuid:d0f89fb8-bb07-499d-bff4-29b074ed17ef"},"language":"en","primary_location":{"id":"pmh:oai:tudelft.nl:uuid:d0f89fb8-bb07-499d-bff4-29b074ed17ef","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:d0f89fb8-bb07-499d-bff4-29b074ed17ef","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.4233/uuid:d0f89fb8-bb07-499d-bff4-29b074ed17ef","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lin, Yancong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lin, Yancong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.7408999800682068,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.7408999800682068,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.08879999816417694,"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/T13282","display_name":"Automated Road and Building Extraction","score":0.05389999970793724,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/artificial-neural-network","display_name":"Artificial neural network","score":0.5805000066757202},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5738000273704529},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5131999850273132},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4975000023841858},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46810001134872437},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.453900009393692},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4309999942779541},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38109999895095825},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.3653999865055084}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7583000063896179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6699000000953674},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5805000066757202},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5738000273704529},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5131999850273132},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4975000023841858},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4309999942779541},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42570000886917114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C56435381","wikidata":"https://www.wikidata.org/wiki/Q1196371","display_name":"Geometric transformation","level":3,"score":0.3481999933719635},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C200518788","wikidata":"https://www.wikidata.org/wiki/Q195076","display_name":"Hough transform","level":3,"score":0.3294000029563904},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C32990609","wikidata":"https://www.wikidata.org/wiki/Q306542","display_name":"Transformation geometry","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31439998745918274},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:tudelft.nl:uuid:d0f89fb8-bb07-499d-bff4-29b074ed17ef","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:d0f89fb8-bb07-499d-bff4-29b074ed17ef","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},{"id":"doi:10.4233/uuid:d0f89fb8-bb07-499d-bff4-29b074ed17ef","is_oa":true,"landing_page_url":"https://doi.org/10.4233/uuid:d0f89fb8-bb07-499d-bff4-29b074ed17ef","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"doi:10.4233/uuid:d0f89fb8-bb07-499d-bff4-29b074ed17ef","is_oa":true,"landing_page_url":"https://doi.org/10.4233/uuid:d0f89fb8-bb07-499d-bff4-29b074ed17ef","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"sustainable_development_goals":[{"score":0.794599711894989,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"humanly":[1],"constructed":[2],"world":[3,14,70,85],"is":[4,15,139,156,174],"well-organized":[5],"in":[6,79,88,150,188,336,376],"space.":[7,379],"A":[8,153],"prominent":[9],"feature":[10],"of":[11,18,29,34,82,159,166,185,264,281,314,333,399,413,418,430],"this":[12,111,218,270,457],"artificial":[13],"the":[16,68,83,89,137,151,157,164,183,202,229,236,250,273,290,318,331,362,373,377,390,397,414,419,439,471],"presence":[17],"repetitive":[19],"structures":[20,38],"and":[21,32,39,100,211,267,416,421],"coherent":[22],"patterns,":[23],"such":[24,107],"as":[25,71,108,163,428],"lines,":[26,210],"junctions,":[27],"wireframes":[28],"a":[30,35,129,189,205,213,261,278,286,410,435,444],"building,":[31],"footprints":[33],"city.":[36],"These":[37],"patterns":[40],"facilitate":[41],"visual":[42,69],"scene":[43],"understanding":[44,81],"by":[45,117,193,276,405],"providing":[46],"abundant":[47],"geometry":[48,355],"information.":[49],"Humans":[50],"can":[51,442],"easily":[52],"recognize":[53],"diverse":[54],"geometric":[55,84,195,288,334,463],"structures.":[56],"However,":[57],"we":[58,72,248,341,365,395,432,459],"wonder":[59],"how":[60],"to":[61,66,133,181,216,255,370],"instruct":[62],"an":[63,300],"autonomous":[64],"agent":[65],"interpret":[67],"do?":[73],"There":[74],"has":[75,113],"been":[76,114],"great":[77],"interest":[78],"automatic":[80],"from":[86,124,347,403,451],"images":[87,404],"past":[90],"few":[91],"decades.":[92],"Conventional":[93],"approaches":[94],"first":[95],"detect":[96],"hand-crafted":[97],"edge":[98],"features":[99,123],"then":[101],"group":[102],"them":[103],"into":[104,197,220,356,465],"parametric":[105],"shapes":[106,402],"lines.":[109],"Recently,":[110],"strategy":[112],"gradually":[115],"replaced":[116],"deep":[118,167,467],"neural":[119,148,186,221],"networks":[120,149,168,187,222],"because":[121],"learning":[122,448,468],"large":[125,312],"annotated":[126,476],"datasets":[127,326],"gives":[128],"richer":[130],"representation":[131],"compared":[132],"hand-designed":[134],"features.":[135],"Although":[136],"progress":[138],"inspiring,":[140],"there":[141],"are":[142],"still":[143],"several":[144],"concerns":[145],"on":[146,239,311,424,434],"deploying":[147],"real-world.":[152],"primary":[154],"concern":[155],"availability":[158],"massive":[160,279],"labeled":[161,265],"data,":[162,266],"performance":[165,184,275,323,386],"deteriorates":[169],"substantially":[170,238],"when":[171],"training":[172,245,315],"data":[173,191,224,338],"scarce.":[175],"This":[176],"thesis":[177,458],"introduces":[178],"novel":[179],"strategies":[180],"enhance":[182],"small":[190,262],"regime,":[192],"adding":[194],"priors":[196,254,335,464],"learning.":[198,227],"We":[199,284,298,350,408],"start":[200],"with":[201,242,456],"Hough":[203,251],"Transform,":[204],"well-known":[206],"prior":[207,219],"for":[208,223,294,303,447,473],"straight":[209],"offer":[212],"principled":[214],"way":[215],"add":[217],"efficient":[225],"end-to-end":[226,301],"On":[228],"wireframe":[230],"parsing":[231],"task,":[232],"our":[233],"model":[234,320,381],"advances":[235],"state-of-the-art":[237],"various":[240],"subsets":[241],"much":[243],"less":[244],"data.":[246,283,477],"Subsequently,":[247],"extend":[249],"Transform":[252],"line":[253],"semi-supervised":[256],"lane":[257],"detection,":[258],"only":[259,383],"requiring":[260],"amount":[263,280],"show":[268,460],"that":[269,438,461],"approach":[271],"improves":[272,384],"overall":[274,385],"leveraging":[277],"unlabeled":[282],"explore":[285,396],"second":[287],"prior,":[289],"Gaussian":[291],"sphere":[292],"mapping,":[293],"vanishing":[295,307],"point":[296],"detection.":[297],"present":[299],"framework":[302],"detecting":[304,343,400,425],"multiple":[305,325],"non-orthogonal":[306],"points":[308],"without":[309,327],"relying":[310],"quantities":[313],"samples.":[316],"Moreover,":[317],"proposed":[319],"exhibits":[321],"consistent":[322],"across":[324],"fine-tuning,":[328],"thus":[329],"demonstrating":[330],"effectiveness":[332],"tackling":[337],"variation.":[339],"Next,":[340],"study":[342],"3D":[344,353],"mirror":[345,354],"symmetry":[346,358],"single-view":[348],"images.":[349,453],"explicitly":[351],"incorporate":[352],"identifying":[357],"planes.":[359],"To":[360],"reduce":[361],"computational":[363],"footprint,":[364],"design":[366],"multi-stage":[367],"spherical":[368],"convolutions":[369],"hierarchically":[371],"pinpoint":[372],"optimal":[374],"plane":[375],"parameter":[378],"Our":[380],"not":[382],"but":[387],"also":[388],"reduces":[389],"inference":[391],"latency":[392],"substantially.":[393],"Finally,":[394],"possibility":[398],"polygonal":[401,449],"using":[406],"transformers.":[407],"provide":[409],"full":[411],"picture":[412],"strength":[415],"weakness":[417],"auto-regressive":[420,440],"parallel":[422],"transformers":[423,441],"polygons":[426],"viewed":[427],"collections":[429],"points.":[431],"demonstrate":[433],"toy":[436],"dataset":[437],"be":[443],"reasonable":[445],"option":[446],"representations":[450],"real-world":[452],"Taken":[454],"together,":[455],"incorporating":[462],"modern":[466],"allows":[469],"reducing":[470],"need":[472],"expensive,":[474],"manually":[475]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}