{"id":"https://openalex.org/W3135861835","doi":"https://doi.org/10.1109/icra48506.2021.9561441","title":"Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation","display_name":"Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3135861835","doi":"https://doi.org/10.1109/icra48506.2021.9561441","mag":"3135861835"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561441","doi":"https://doi.org/10.1109/icra48506.2021.9561441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561441","pdf_url":null,"source":{"id":"https://openalex.org/S4210217939","display_name":"Proceedings - IEEE International Conference on Robotics and Automation/Proceedings","issn_l":"1050-4729","issn":["1050-4729","2577-087X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"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"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.02451","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043042113","display_name":"Hemang Chawla","orcid":"https://orcid.org/0000-0002-5999-6901","observed_orcids":["https://orcid.org/0000-0002-5999-6901"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hemang Chawla","raw_affiliation_strings":["Navinfo Europe,The Advanced Research Lab,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navinfo Europe,The Advanced Research Lab,The Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082972838","display_name":"Arnav Varma","orcid":"https://orcid.org/0000-0002-5919-0449","observed_orcids":["https://orcid.org/0000-0002-5919-0449"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arnav Varma","raw_affiliation_strings":["Navinfo Europe,The Advanced Research Lab,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navinfo Europe,The Advanced Research Lab,The Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047435371","display_name":"Elahe Arani","orcid":"https://orcid.org/0000-0002-0952-7007","observed_orcids":["https://orcid.org/0000-0002-0952-7007"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elahe Arani","raw_affiliation_strings":["Navinfo Europe,The Advanced Research Lab,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navinfo Europe,The Advanced Research Lab,The Netherlands","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028650455","display_name":"Bahram Zonooz","orcid":"https://orcid.org/0000-0003-4124-3394","observed_orcids":["https://orcid.org/0000-0003-4124-3394"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bahram Zonooz","raw_affiliation_strings":["Navinfo Europe,The Advanced Research Lab,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navinfo Europe,The Advanced Research Lab,The Netherlands","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7052,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.89699285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5140","last_page":"5146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9951000213623047,"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":0.9951000213623047,"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":0.0032999999821186066,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monocular-depth-estimation","display_name":"monocular depth estimation","score":0.8230000138282776},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.996999979019165},{"id":"https://openalex.org/keywords/scale-consistency","display_name":"scale consistency","score":0.7910000085830688},{"id":"https://openalex.org/keywords/gps","display_name":"GPS","score":0.6539999842643738},{"id":"https://openalex.org/keywords/multimodal-training","display_name":"multimodal training","score":0.7070000171661377},{"id":"https://openalex.org/keywords/long-video-sequences","display_name":"long video sequences","score":0.5740000009536743},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.7720000147819519},{"id":"https://openalex.org/keywords/scene-understanding","display_name":"scene understanding","score":0.597000002861023},{"id":"https://openalex.org/keywords/feature-representation","display_name":"feature representation","score":0.4480000138282776}],"concepts":[{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.8466204404830933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096139192581177},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6536009907722473},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6516252756118774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6480361819267273},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6123296022415161},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5525498390197754},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5083734393119812},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4559744596481323},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41371747851371765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3323988616466522},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.16692417860031128},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.08237171173095703},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07646554708480835},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9561441","doi":"https://doi.org/10.1109/icra48506.2021.9561441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561441","pdf_url":null,"source":{"id":"https://openalex.org/S4210217939","display_name":"Proceedings - IEEE International Conference on Robotics and Automation/Proceedings","issn_l":"1050-4729","issn":["1050-4729","2577-087X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"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:2103.02451","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.02451","pdf_url":"https://arxiv.org/pdf/2103.02451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"mag:3135861835","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2103.02451v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2103.02451","doi":"https://doi.org/10.48550/arxiv.2103.02451","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.02451","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.02451","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.02451","pdf_url":"https://arxiv.org/pdf/2103.02451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135861835.pdf","grobid_xml":"https://content.openalex.org/works/W3135861835.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1545195129","https://openalex.org/W1612997784","https://openalex.org/W2115579991","https://openalex.org/W2132947399","https://openalex.org/W2171740948","https://openalex.org/W2184188583","https://openalex.org/W2300779272","https://openalex.org/W2340897893","https://openalex.org/W2520707372","https://openalex.org/W2609883120","https://openalex.org/W2750215633","https://openalex.org/W2767290858","https://openalex.org/W2774616426","https://openalex.org/W2785512290","https://openalex.org/W2789734266","https://openalex.org/W2804176584","https://openalex.org/W2806446538","https://openalex.org/W2808456995","https://openalex.org/W2810665122","https://openalex.org/W2886322387","https://openalex.org/W2887825894","https://openalex.org/W2899117197","https://openalex.org/W2920827956","https://openalex.org/W2935920407","https://openalex.org/W2942955593","https://openalex.org/W2949115101","https://openalex.org/W2949208911","https://openalex.org/W2959581809","https://openalex.org/W2963412495","https://openalex.org/W2963488291","https://openalex.org/W2963583471","https://openalex.org/W2963732628","https://openalex.org/W2963732666","https://openalex.org/W2963808267","https://openalex.org/W2964193874","https://openalex.org/W2966444020","https://openalex.org/W2970369664","https://openalex.org/W2979208272","https://openalex.org/W2990946490","https://openalex.org/W2991840778","https://openalex.org/W3002133910","https://openalex.org/W3004144522","https://openalex.org/W3016970897","https://openalex.org/W3042969293","https://openalex.org/W3044406175","https://openalex.org/W3129944514"],"related_works":["https://openalex.org/W4281400708","https://openalex.org/W4367154434","https://openalex.org/W4285102356","https://openalex.org/W4323338576","https://openalex.org/W3127615386","https://openalex.org/W4250871918","https://openalex.org/W7125433104","https://openalex.org/W3201971426","https://openalex.org/W7220384195","https://openalex.org/W7163031407"],"abstract_inverted_index":{"Dense":[0],"depth":[1,105],"estimation":[2,106],"is":[3,54,79],"essential":[4],"to":[5,44],"scene-understanding":[6],"for":[7],"autonomous":[8],"driving.":[9],"However,":[10],"recent":[11],"self-supervised":[12],"approaches":[13],"on":[14,97],"monocular":[15],"videos":[16],"suffer":[17],"from":[18,25],"scale-inconsistency":[19],"across":[20],"long":[21],"sequences.":[22],"Utilizing":[23],"data":[24],"the":[26,46,52,58,72,82,110],"ubiquitously":[27],"copresent":[28],"global":[29],"positioning":[30],"systems":[31],"(GPS),":[32],"we":[33,100],"tackle":[34],"this":[35],"challenge":[36],"by":[37],"proposing":[38],"a":[39,75],"dynamically-weighted":[40],"GPS-to-Scale":[41],"(g2s)":[42],"loss":[43],"complement":[45],"appearance-based":[47],"losses.":[48],"We":[49],"emphasize":[50],"that":[51,78],"GPS":[53,73,117],"needed":[55],"only":[56],"during":[57,107],"multimodal":[59],"training,":[60],"and":[61,85,103],"not":[62],"at":[63],"inference.":[64],"The":[65],"relative":[66],"distance":[67],"between":[68],"frames":[69],"captured":[70],"through":[71],"provides":[74],"scale":[76],"signal":[77],"independent":[80],"of":[81],"camera":[83],"setup":[84],"scene":[86],"distribution,":[87],"resulting":[88],"in":[89],"richer":[90],"learned":[91],"feature":[92],"representations.":[93],"Through":[94],"extensive":[95],"evaluation":[96],"multiple":[98],"datasets,":[99],"demonstrate":[101],"scale-consistent":[102],"-aware":[104],"inference,":[108],"improving":[109],"performance":[111],"even":[112],"when":[113],"training":[114],"with":[115],"low-frequency":[116],"data.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-03-15T00:00:00"}