{"id":"https://openalex.org/W2963412495","doi":"https://doi.org/10.1609/aaai.v33i01.33018001","title":"Depth Prediction without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos","display_name":"Depth Prediction without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2963412495","doi":"https://doi.org/10.1609/aaai.v33i01.33018001","mag":"2963412495"},"language":"en","primary_location":{"id":"pmh:oai:ojs.aaai.org:article/4801","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},"type":"article","indexed_in":[],"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/A5052810777","display_name":"Vincent Casser","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Casser, Vincent","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022418359","display_name":"S\u00f6ren Pirk","orcid":"https://orcid.org/0000-0003-1937-9797"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pirk, Soeren","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023703380","display_name":"Reza Mahjourian","orcid":"https://orcid.org/0000-0002-4457-8395"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahjourian, Reza","raw_affiliation_strings":["University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066709641","display_name":"Anelia Angelova","orcid":"https://orcid.org/0000-0003-1822-7943"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Angelova, Anelia","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":37.627,"has_fulltext":true,"cited_by_count":493,"citation_normalized_percentile":{"value":0.99900732,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9986000061035156,"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":0.9986000061035156,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.998199999332428,"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":0.996399998664856,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.8137688040733337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7846589088439941},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7181137800216675},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6760587096214294},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5259699821472168},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5064839124679565},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5030021071434021},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5016443729400635},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.459317684173584},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4368690848350525},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4282810389995575}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8137688040733337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7846589088439941},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7181137800216675},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6760587096214294},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5259699821472168},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5064839124679565},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5030021071434021},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5016443729400635},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.459317684173584},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4368690848350525},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4282810389995575},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:ojs.aaai.org:article/4801","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W337610345","https://openalex.org/W1545195129","https://openalex.org/W1803059841","https://openalex.org/W1899309388","https://openalex.org/W2074254947","https://openalex.org/W2115579991","https://openalex.org/W2133665775","https://openalex.org/W2300779272","https://openalex.org/W2340897893","https://openalex.org/W2409352305","https://openalex.org/W2520707372","https://openalex.org/W2561074213","https://openalex.org/W2608018946","https://openalex.org/W2609883120","https://openalex.org/W2767981409","https://openalex.org/W2810554001","https://openalex.org/W2951234442","https://openalex.org/W2962807621","https://openalex.org/W2962816904","https://openalex.org/W2963549785","https://openalex.org/W2963583471","https://openalex.org/W2963654727","https://openalex.org/W2963706662","https://openalex.org/W2963906250","https://openalex.org/W2985775862"],"related_works":["https://openalex.org/W1508899372","https://openalex.org/W200819717","https://openalex.org/W1991834176","https://openalex.org/W2012658348","https://openalex.org/W2039460805","https://openalex.org/W4250956039","https://openalex.org/W2032269556","https://openalex.org/W4240485100","https://openalex.org/W3201126466","https://openalex.org/W2056130799"],"abstract_inverted_index":{"Learning":[0],"to":[1,77,84,92,99,134,140,165,214],"predict":[2],"scene":[3,27,110],"depth":[4,28,176],"from":[5,90,122],"RGB":[6],"inputs":[7],"is":[8,34,75,82,98,132,191],"a":[9,67,184],"challenging":[10],"task":[11],"both":[12],"for":[13,50,208],"indoor":[14,93,215],"and":[15,29,46,81,111,117,173,180],"outdoor":[16],"robot":[17,30,209],"navigation.":[18],"In":[19],"this":[20,222],"work":[21,53],"we":[22],"address":[23],"unsupervised":[24,55],"learning":[25,57,105,136],"of":[26,186,192],"ego-motion":[31,116],"where":[32],"supervision":[33,172],"provided":[35],"by":[36,107,201],"monocular":[37,123],"videos,":[38],"as":[39,125,171,195],"cameras":[40],"are":[41,120,161],"the":[42,63,104,109,112,138,166],"cheapest,":[43],"least":[44],"restrictive":[45],"most":[47],"ubiquitous":[48],"sensor":[49],"robotics.":[51],"Previous":[52],"in":[54,62,103,163,211],"image-to-depth":[56],"has":[58],"established":[59],"strong":[60],"baselines":[61],"domain.":[64],"We":[65],"propose":[66],"novel":[68],"approach":[69,145,190],"which":[70,168,182],"produces":[71],"higher":[72],"quality":[73,164],"results,":[74],"able":[76],"model":[78],"moving":[79],"objects":[80],"shown":[83],"transfer":[85,198],"across":[86,199],"data":[87,206],"domains,":[88],"e.g.":[89,155],"outdoors":[91],"scenes.":[94],"The":[95,143,189,218],"main":[96],"idea":[97],"introduce":[100],"geometric":[101],"structure":[102],"process,":[106],"modeling":[108],"individual":[113],"objects;":[114],"camera":[115],"object":[118,187],"motions":[119],"learned":[121,157],"videos":[124],"input.":[126],"Furthermore":[127],"an":[128],"online":[129],"refinement":[130],"method":[131],"introduced":[133],"adapt":[135],"on":[137,178,205],"fly":[139],"unknown":[141],"domains.":[142],"proposed":[144],"outperforms":[146],"all":[147],"state-of-the-art":[148],"approaches,":[149],"including":[150],"those":[151],"that":[152],"handle":[153],"motion":[154],"through":[156],"flow.":[158],"Our":[159],"results":[160],"comparable":[162],"ones":[167],"used":[169],"stereo":[170],"significantly":[174],"improve":[175],"prediction":[177],"scenes":[179,213],"datasets":[181],"contain":[183],"lot":[185],"motion.":[188],"practical":[193],"relevance,":[194],"it":[196],"allows":[197],"environments,":[200],"transferring":[202],"models":[203],"trained":[204],"collected":[207],"navigation":[210,216],"urban":[212],"settings.":[217],"code":[219],"associated":[220],"with":[221],"paper":[223],"can":[224],"be":[225],"found":[226],"at":[227],"https://sites.google.com/view/struct2depth.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":50},{"year":2023,"cited_by_count":72},{"year":2022,"cited_by_count":90},{"year":2021,"cited_by_count":110},{"year":2020,"cited_by_count":106},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}