{"id":"https://openalex.org/W3101242164","doi":"https://doi.org/10.1109/icra48506.2021.9561793","title":"Learning a Geometric Representation for Data-Efficient Depth Estimation via Gradient Field and Contrastive Loss","display_name":"Learning a Geometric Representation for Data-Efficient Depth Estimation via Gradient Field and Contrastive Loss","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3101242164","doi":"https://doi.org/10.1109/icra48506.2021.9561793","mag":"3101242164"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.03207","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037135304","display_name":"Dongseok Shim","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongseok Shim","raw_affiliation_strings":["Seoul National University,Department of Mechanical and Aerospace Engineering,Gwanak-gu, Seoul,Korea,08826"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Mechanical and Aerospace Engineering,Gwanak-gu, Seoul,Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073996122","display_name":"H. Jin Kim","orcid":"https://orcid.org/0000-0002-6819-1136"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"H. Jin Kim","raw_affiliation_strings":["Seoul National University,Department of Mechanical and Aerospace Engineering,Gwanak-gu, Seoul,Korea,08826","Seoul National Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Mechanical and Aerospace Engineering,Gwanak-gu, Seoul,Korea,08826","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National Univ.#TAB#","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13634","last_page":"13640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9998000264167786,"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":0.9998000264167786,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9958999752998352,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7821217775344849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7426348328590393},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6910438537597656},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6469347476959229},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5641890168190002},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5272293090820312},{"id":"https://openalex.org/keywords/depth-map","display_name":"Depth map","score":0.526445746421814},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5035075545310974},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.49665170907974243},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4459715485572815},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3840678334236145},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2812328338623047}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7821217775344849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426348328590393},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6910438537597656},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6469347476959229},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5641890168190002},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5272293090820312},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.526445746421814},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5035075545310974},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.49665170907974243},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4459715485572815},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3840678334236145},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2812328338623047},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9561793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.03207","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.03207","pdf_url":"https://arxiv.org/pdf/2011.03207","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3101242164","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.03207","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.03207","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.03207","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.03207","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.03207","pdf_url":"https://arxiv.org/pdf/2011.03207","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3101242164.pdf","grobid_xml":"https://content.openalex.org/works/W3101242164.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W343636949","https://openalex.org/W1498436455","https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1803059841","https://openalex.org/W1901129140","https://openalex.org/W1905829557","https://openalex.org/W2074254947","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2132947399","https://openalex.org/W2138621090","https://openalex.org/W2144796873","https://openalex.org/W2145023731","https://openalex.org/W2171740948","https://openalex.org/W2194775991","https://openalex.org/W2300779272","https://openalex.org/W2321533354","https://openalex.org/W2520707372","https://openalex.org/W2609883120","https://openalex.org/W2776033207","https://openalex.org/W2798991696","https://openalex.org/W2842511635","https://openalex.org/W2907670226","https://openalex.org/W2944828972","https://openalex.org/W2962742544","https://openalex.org/W2962960377","https://openalex.org/W2963446712","https://openalex.org/W2963465221","https://openalex.org/W2963488291","https://openalex.org/W2963591054","https://openalex.org/W2967115342","https://openalex.org/W2970971581","https://openalex.org/W2985775862","https://openalex.org/W2991172647","https://openalex.org/W3009561768","https://openalex.org/W3021539629","https://openalex.org/W3034978746","https://openalex.org/W3035058308","https://openalex.org/W3035524453","https://openalex.org/W6639633739","https://openalex.org/W6639824700","https://openalex.org/W6685261749","https://openalex.org/W6697658144","https://openalex.org/W6725739302","https://openalex.org/W6726644806","https://openalex.org/W6736677999","https://openalex.org/W6747899497","https://openalex.org/W6757246177","https://openalex.org/W6762573206","https://openalex.org/W6766978945","https://openalex.org/W6774314701","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W3031898827","https://openalex.org/W2981347100","https://openalex.org/W3034604951","https://openalex.org/W2994589730","https://openalex.org/W3092756309","https://openalex.org/W2903640603","https://openalex.org/W2963788359","https://openalex.org/W3023173229","https://openalex.org/W2963032410","https://openalex.org/W3089762353","https://openalex.org/W3194548235","https://openalex.org/W3088064919","https://openalex.org/W3173409262","https://openalex.org/W3175903087","https://openalex.org/W2905120940","https://openalex.org/W2343077198","https://openalex.org/W2922249476","https://openalex.org/W3135387182","https://openalex.org/W2561242184","https://openalex.org/W3174575212"],"abstract_inverted_index":{"Estimating":[0],"a":[1,5,24,39,127,147,158],"depth":[2,26,79,106,123,154,184],"map":[3,155],"from":[4],"single":[6],"RGB":[7,64],"image":[8],"has":[9],"been":[10],"investigated":[11],"widely":[12],"for":[13],"localization,":[14],"mapping,":[15],"and":[16,56,125,197],"3-":[17],"dimensional":[18],"object":[19,102],"detection.":[20],"Recent":[21],"studies":[22],"on":[23,31,88,122,210],"single-view":[25],"estimation":[27,124,185],"are":[28,53,86],"mostly":[29],"based":[30],"deep":[32],"Convolutional":[33],"neural":[34],"Networks":[35],"(ConvNets)":[36],"which":[37,66],"require":[38],"large":[40],"amount":[41,161],"of":[42,76,93,162,172,201],"training":[43],"data":[44,203],"paired":[45],"with":[46,132,143,157,180],"densely":[47],"annotated":[48,163],"labels.":[49,80],"Depth":[50,213],"annotation":[51],"tasks":[52],"both":[54],"expensive":[55],"inefficient,":[57],"so":[58],"it":[59],"is":[60,170],"inevitable":[61],"to":[62,72,95,136,207],"leverage":[63],"images":[65,94],"can":[67,151],"be":[68],"collected":[69],"very":[70],"easily":[71],"boost":[73],"the":[74,90,97,140,149,153,173,190,199,211],"performance":[75,98],"ConvNets":[77,138],"without":[78],"However,":[81],"most":[82],"self-supervised":[83,129,194],"learning":[84,130,195],"algorithms":[85,196],"focused":[87],"capturing":[89],"semantic":[91],"information":[92,142],"improve":[96],"in":[99,105,204],"classification":[100],"or":[101],"detection,":[103],"not":[104,119],"estimation.":[107],"In":[108],"this":[109],"paper,":[110],"we":[111,176],"show":[112,166],"that":[113,167],"existing":[114],"self-":[115],"supervised":[116],"methods":[117],"do":[118],"perform":[120],"well":[121],"propose":[126],"gradient-based":[128],"algorithm":[131],"momentum":[133],"contrastive":[134],"loss":[135],"help":[137],"extract":[139],"geometric":[141],"unlabeled":[144],"images.":[145],"As":[146],"result,":[148],"network":[150],"estimate":[152],"accurately":[156],"relatively":[159],"small":[160],"data.":[164],"To":[165],"our":[168,178],"method":[169,179,188],"independent":[171],"model":[174],"structure,":[175],"evaluate":[177],"two":[181],"different":[182],"monocular":[183],"algorithms.":[186],"Our":[187],"outperforms":[189],"previous":[191],"state-of-the-":[192],"art":[193],"shows":[198],"efficiency":[200],"labeled":[202],"triple":[205],"compared":[206],"random":[208],"initialization":[209],"NYU":[212],"v2":[214],"dataset.":[215]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}