{"id":"https://openalex.org/W4401414068","doi":"https://doi.org/10.1109/icra57147.2024.10610075","title":"Self-Supervised Learning of Monocular Visual Odometry and Depth with Uncertainty-Aware Scale Consistency","display_name":"Self-Supervised Learning of Monocular Visual Odometry and Depth with Uncertainty-Aware Scale Consistency","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414068","doi":"https://doi.org/10.1109/icra57147.2024.10610075"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5100709173","display_name":"Changhao Wang","orcid":"https://orcid.org/0000-0002-5753-1991"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhao Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Visual Intelligent Processing Laboratory, School of Electronics and Information,Xi’an Shannxi,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Visual Intelligent Processing Laboratory, School of Electronics and Information,Xi’an Shannxi,P.R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087863930","display_name":"Guanwen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanwen Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Visual Intelligent Processing Laboratory, School of Electronics and Information,Xi’an Shannxi,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Visual Intelligent Processing Laboratory, School of Electronics and Information,Xi’an Shannxi,P.R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015473700","display_name":"Wei Zhou","orcid":"https://orcid.org/0000-0003-4300-811X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["Northwestern Polytechnical University,Visual Intelligent Processing Laboratory, School of Electronics and Information,Xi’an Shannxi,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Visual Intelligent Processing Laboratory, School of Electronics and Information,Xi’an Shannxi,P.R. China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8749,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7440076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3984","last_page":"3990"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T12549","display_name":"Image and Object Detection Techniques","score":0.9993000030517578,"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/visual-odometry","display_name":"Visual odometry","score":0.8598402738571167},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.7632367610931396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7262191772460938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6713773608207703},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6315891742706299},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6290836930274963},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5648238658905029},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.14176130294799805},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0885118842124939},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0688772201538086}],"concepts":[{"id":"https://openalex.org/C5799516","wikidata":"https://www.wikidata.org/wiki/Q4110915","display_name":"Visual odometry","level":3,"score":0.8598402738571167},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7632367610931396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7262191772460938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6713773608207703},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6315891742706299},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6290836930274963},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5648238658905029},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.14176130294799805},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0885118842124939},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0688772201538086}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336567","display_name":"Natural Science Basic Research Program of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W612478963","https://openalex.org/W1612997784","https://openalex.org/W1861492603","https://openalex.org/W1970504153","https://openalex.org/W2033819227","https://openalex.org/W2085261163","https://openalex.org/W2102481828","https://openalex.org/W2117539524","https://openalex.org/W2133665775","https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2300779272","https://openalex.org/W2474281075","https://openalex.org/W2520707372","https://openalex.org/W2535547924","https://openalex.org/W2564632156","https://openalex.org/W2600383743","https://openalex.org/W2609883120","https://openalex.org/W2890949887","https://openalex.org/W2895192073","https://openalex.org/W2899771611","https://openalex.org/W2951234442","https://openalex.org/W2962816904","https://openalex.org/W2963488291","https://openalex.org/W2963583471","https://openalex.org/W2967059695","https://openalex.org/W2971000934","https://openalex.org/W2981732213","https://openalex.org/W2985775862","https://openalex.org/W2990946490","https://openalex.org/W3034364596","https://openalex.org/W3035056458","https://openalex.org/W3043075211","https://openalex.org/W3091687063","https://openalex.org/W3102327032","https://openalex.org/W3173274332","https://openalex.org/W3174211490","https://openalex.org/W3180341139","https://openalex.org/W3200732573","https://openalex.org/W3204559841","https://openalex.org/W3206296944","https://openalex.org/W4312725059","https://openalex.org/W4320036904","https://openalex.org/W4321504701","https://openalex.org/W6685261749","https://openalex.org/W6735443497","https://openalex.org/W6767088534","https://openalex.org/W6771609694"],"related_works":["https://openalex.org/W4386394365","https://openalex.org/W3006563365","https://openalex.org/W2954249689","https://openalex.org/W2626414811","https://openalex.org/W4313484789","https://openalex.org/W2001736731","https://openalex.org/W2913604885","https://openalex.org/W4302306787","https://openalex.org/W4300939778","https://openalex.org/W2950564770"],"abstract_inverted_index":{"The":[0,112],"inherent":[1],"scale":[2,72,89,110],"ambiguity":[3],"issue":[4],"greatly":[5],"limits":[6],"the":[7,48,51,56,103,109,121,140],"performance":[8,145],"of":[9,18,26,50],"monocular":[10,133],"visual":[11,82],"odometry.":[12],"In":[13],"recent":[14],"years,":[15],"a":[16,41,80,98],"variety":[17],"methods":[19,46],"have":[20],"been":[21],"proposed":[22,113,141],"for":[23,107],"self-supervised":[24],"learning":[25,84,99],"ego-motion":[27],"and":[28,69,120,135],"depth":[29,39,52,64,105,148],"estimation,":[30],"incorporating":[31],"specifically":[32],"designed":[33],"scale-consistency":[34],"constraints":[35],"that":[36,125],"utilize":[37],"estimated":[38],"as":[40],"reference.":[42],"However,":[43],"these":[44,76],"existing":[45],"neglect":[47],"influence":[49],"uncertainty":[53,106],"introduced":[54],"by":[55],"dominant":[57],"photometric":[58],"loss,":[59],"which":[60],"leads":[61],"to":[62,101],"unreliable":[63],"estimation":[65],"in":[66,92],"difficult":[67],"regions":[68],"detrimentally":[70],"affects":[71],"alignment.":[73],"To":[74],"solve":[75],"problems,":[77],"we":[78,96],"introduces":[79],"feature-based":[81],"odometry":[83],"system":[85,127],"with":[86],"an":[87],"effective":[88],"recovery":[90],"strategy":[91],"this":[93],"paper.":[94],"Additionally,":[95],"propose":[97],"method":[100,114,142],"estimate":[102],"photometric-sensitive":[104],"guiding":[108],"recovery.":[111],"is":[115],"evaluated":[116],"on":[117,146],"KITTI":[118,147],"odometry,":[119],"experimental":[122],"results":[123],"demonstrate":[124],"our":[126],"can":[128],"predict":[129],"scale-consistent":[130],"trajectories":[131],"from":[132],"videos":[134],"achieves":[136,143],"state-of-the-art":[137],"performance.":[138],"Moreover,":[139],"competitive":[144],"estimation.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}