{"id":"https://openalex.org/W3205538826","doi":"https://doi.org/10.1109/icra48506.2021.9561508","title":"Self-Supervised Learning for Monocular Depth Estimation on Minimally Invasive Surgery Scenes","display_name":"Self-Supervised Learning for Monocular Depth Estimation on Minimally Invasive Surgery Scenes","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3205538826","doi":"https://doi.org/10.1109/icra48506.2021.9561508","mag":"3205538826"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561508","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":"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":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, 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":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, 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":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503795","display_name":"Baochang Zhang","orcid":"https://orcid.org/0000-0001-6167-4760"},"institutions":[{"id":"https://openalex.org/I4210159500","display_name":"Shenzhen Academy of Aerospace Technology","ror":"https://ror.org/05etzsm06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210159500"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baochang Zhang","raw_affiliation_strings":["Shenzhen Academy of Aerospace Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Academy of Aerospace Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210159500"]}]},{"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":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084387605","display_name":"Dianmin Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]},{"id":"https://openalex.org/I4210100830","display_name":"Shandong Tumor Hospital","ror":"https://ror.org/01413r497","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210100830"]},{"id":"https://openalex.org/I4210163399","display_name":"Shandong First Medical University","ror":"https://ror.org/05jb9pq57","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163399"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dianmin Sun","raw_affiliation_strings":["Shandong Cancer Hospital, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Cancer Hospital, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I4210163399","https://openalex.org/I4210100830","https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003875781","display_name":"David Doermann","orcid":"https://orcid.org/0000-0003-1639-4561"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Doermann","raw_affiliation_strings":["University at Buffalo, Buffalo, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo, Buffalo, USA","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8732,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.76132643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7159","last_page":"7165"},"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/T11019","display_name":"Image Enhancement Techniques","score":0.9940000176429749,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9866999983787537,"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/computer-science","display_name":"Computer science","score":0.7877644896507263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7714359760284424},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.7096619009971619},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.7083268165588379},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6610360145568848},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6180474758148193},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5192106366157532},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.509262204170227},{"id":"https://openalex.org/keywords/brightness","display_name":"Brightness","score":0.4934166967868805},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4927988350391388},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.48038631677627563},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47575873136520386},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4634404480457306},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.4579635262489319},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4550110697746277},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3579360842704773},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19421029090881348},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16046226024627686},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10920673608779907},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10788017511367798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7877644896507263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7714359760284424},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.7096619009971619},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7083268165588379},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6610360145568848},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6180474758148193},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5192106366157532},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.509262204170227},{"id":"https://openalex.org/C125245961","wikidata":"https://www.wikidata.org/wiki/Q221656","display_name":"Brightness","level":2,"score":0.4934166967868805},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4927988350391388},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.48038631677627563},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47575873136520386},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4634404480457306},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.4579635262489319},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4550110697746277},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3579360842704773},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19421029090881348},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16046226024627686},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10920673608779907},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10788017511367798},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9561508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561508","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.8500000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1522301498","https://openalex.org/W2109255472","https://openalex.org/W2133665775","https://openalex.org/W2150066425","https://openalex.org/W2171740948","https://openalex.org/W2194775991","https://openalex.org/W2520707372","https://openalex.org/W2552900565","https://openalex.org/W2560474170","https://openalex.org/W2582073395","https://openalex.org/W2609883120","https://openalex.org/W2614788194","https://openalex.org/W2899771611","https://openalex.org/W2951234442","https://openalex.org/W2962816904","https://openalex.org/W2962900571","https://openalex.org/W2964121744","https://openalex.org/W2964156315","https://openalex.org/W2985775862","https://openalex.org/W2989184872","https://openalex.org/W3009257710","https://openalex.org/W3035056458","https://openalex.org/W3035434014","https://openalex.org/W3119959063","https://openalex.org/W4298129340","https://openalex.org/W6618372016","https://openalex.org/W6631190155","https://openalex.org/W6685261749","https://openalex.org/W6726644806","https://openalex.org/W6736677999","https://openalex.org/W6756040250","https://openalex.org/W6774628140","https://openalex.org/W6787724516"],"related_works":["https://openalex.org/W2393022482","https://openalex.org/W2377346130","https://openalex.org/W2361092061","https://openalex.org/W34817178","https://openalex.org/W2319775965","https://openalex.org/W2357314690","https://openalex.org/W2795976185","https://openalex.org/W2191886813","https://openalex.org/W2163394011","https://openalex.org/W2353606679"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,47,107],"algorithms":[2],"that":[3],"compute":[4],"depth":[5],"map":[6],"from":[7,40],"monocular":[8],"videos":[9,34,122],"have":[10,18],"achieved":[11],"remarkable":[12],"performance":[13],"on":[14,123],"urban":[15,121],"scenes":[16],"and":[17,44,71],"been":[19],"applied":[20,30],"extensively.":[21],"These":[22],"techniques":[23],"still":[24],"face":[25],"significant":[26],"challenges,":[27],"however,":[28],"when":[29],"directly":[31],"to":[32,42,75,102,113],"endoscopic":[33],"because":[35],"of":[36],"the":[37,49,54,77,85,104,114,124,127],"brightness":[38,86],"variations":[39],"frame":[41,43],"inadequate":[45,105],"representation":[46,106],"during":[48],"training":[50],"phase.":[51],"Inspired":[52],"by":[53,133],"optical":[55],"flow":[56,79],"for":[57,120],"motion":[58],"alignment":[59],"between":[60],"adjacent":[61,81],"frames,":[62,82],"we":[63,92],"design":[64],"a":[65,94,110,134],"AFNet":[66],"with":[67],"structural":[68],"stability":[69],"loss":[70,74],"residual-based":[72],"smoothness":[73],"learn":[76],"appearance":[78],"across":[80],"which":[83],"handles":[84],"inconsistency":[87],"issue":[88],"efficaciously.":[89],"In":[90,109],"addition,":[91],"propose":[93],"novel":[95],"self-attention":[96],"mechanism":[97],"named":[98],"feature":[99],"scaling":[100],"module":[101],"alleviate":[103],"problem.":[108],"comparison":[111],"study":[112],"current":[115],"state-of-the-art":[116],"self-supervised":[117],"methods":[118,132],"explored":[119],"SCARED":[125],"dataset,":[126],"developed":[128],"model":[129],"surpasses":[130],"existing":[131],"large":[135],"margin.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}