{"id":"https://openalex.org/W4386524116","doi":"https://doi.org/10.1109/tmm.2023.3312950","title":"Unsupervised Monocular Estimation of Depth and Visual Odometry Using Attention and Depth-Pose Consistency Loss","display_name":"Unsupervised Monocular Estimation of Depth and Visual Odometry Using Attention and Depth-Pose Consistency Loss","publication_year":2023,"publication_date":"2023-09-07","ids":{"openalex":"https://openalex.org/W4386524116","doi":"https://doi.org/10.1109/tmm.2023.3312950"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3312950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3312950","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5083983639","display_name":"Xiaogang Song","orcid":"https://orcid.org/0000-0001-9841-9624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaogang Song","raw_affiliation_strings":["School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-9841-9624","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114025502","display_name":"Haoyue Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyue Hu","raw_affiliation_strings":["School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420739","display_name":"Li Liang","orcid":"https://orcid.org/0009-0007-5439-5860"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Liang","raw_affiliation_strings":["School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0007-5439-5860","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031994389","display_name":"Weiwei Shi","orcid":"https://orcid.org/0009-0002-8282-7193"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiwei Shi","raw_affiliation_strings":["School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000799818","display_name":"Guo Xie","orcid":"https://orcid.org/0000-0002-9948-453X"},"institutions":[{"id":"https://openalex.org/I4210131919","display_name":"Xi'an University of Technology","ror":"https://ror.org/038avdt50","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131919"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo Xie","raw_affiliation_strings":["School of Automation and Information Engineering, Xi'an University of Technology, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-9948-453X","affiliations":[{"raw_affiliation_string":"School of Automation and Information Engineering, Xi'an University of Technology, Xi'an, China","institution_ids":["https://openalex.org/I4210131919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100543103","display_name":"Xiaofeng Lu","orcid":"https://orcid.org/0009-0003-2526-0511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofeng Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073391035","display_name":"Xinhong Hei","orcid":"https://orcid.org/0000-0002-6394-0492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinhong Hei","raw_affiliation_strings":["School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-6394-0492","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5824,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91676765,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"3517","last_page":"3529"},"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9987000226974487,"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/T10638","display_name":"Optical measurement and interference techniques","score":0.9983000159263611,"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":0.7898276448249817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7567325830459595},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6810569763183594},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6169369220733643},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6034031510353088},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5561457872390747},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5559624433517456},{"id":"https://openalex.org/keywords/visual-odometry","display_name":"Visual odometry","score":0.4861030578613281},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46483513712882996},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.4637067914009094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45384472608566284},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4433683454990387},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.16063213348388672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7898276448249817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7567325830459595},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6810569763183594},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6169369220733643},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6034031510353088},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5561457872390747},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5559624433517456},{"id":"https://openalex.org/C5799516","wikidata":"https://www.wikidata.org/wiki/Q4110915","display_name":"Visual odometry","level":3,"score":0.4861030578613281},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46483513712882996},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.4637067914009094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45384472608566284},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4433683454990387},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.16063213348388672},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3312950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3312950","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1803059841","https://openalex.org/W1905829557","https://openalex.org/W1915250530","https://openalex.org/W2033819227","https://openalex.org/W2105482032","https://openalex.org/W2115579991","https://openalex.org/W2124907686","https://openalex.org/W2146749082","https://openalex.org/W2300779272","https://openalex.org/W2520707372","https://openalex.org/W2593414960","https://openalex.org/W2609883120","https://openalex.org/W2752782242","https://openalex.org/W2753619605","https://openalex.org/W2768263011","https://openalex.org/W2790058763","https://openalex.org/W2798405286","https://openalex.org/W2884585870","https://openalex.org/W2896991173","https://openalex.org/W2897770165","https://openalex.org/W2962456457","https://openalex.org/W2962741876","https://openalex.org/W2962816904","https://openalex.org/W2963488291","https://openalex.org/W2963583471","https://openalex.org/W2963591054","https://openalex.org/W2963654727","https://openalex.org/W2963906250","https://openalex.org/W2964014680","https://openalex.org/W2964968086","https://openalex.org/W2967550825","https://openalex.org/W2974576232","https://openalex.org/W2982102242","https://openalex.org/W2985775862","https://openalex.org/W2990394353","https://openalex.org/W2990946490","https://openalex.org/W3026510225","https://openalex.org/W3033327942","https://openalex.org/W3034364596","https://openalex.org/W3034552520","https://openalex.org/W3034604951","https://openalex.org/W3035056458","https://openalex.org/W3107156787","https://openalex.org/W3108179104","https://openalex.org/W3118453581","https://openalex.org/W3120797281","https://openalex.org/W3136101383","https://openalex.org/W3145609993","https://openalex.org/W3173409262","https://openalex.org/W3176063055","https://openalex.org/W3191699310","https://openalex.org/W4205932092","https://openalex.org/W4285215809","https://openalex.org/W6618372016","https://openalex.org/W6631190155","https://openalex.org/W6683067110","https://openalex.org/W6685261749","https://openalex.org/W6712702053","https://openalex.org/W6755872202","https://openalex.org/W6767088534","https://openalex.org/W6771531989","https://openalex.org/W6777789446","https://openalex.org/W6785345353"],"related_works":["https://openalex.org/W3006563365","https://openalex.org/W4386394365","https://openalex.org/W2789602789","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"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"shown":[3],"that":[4,173],"joint":[5],"depth":[6,109],"and":[7,46,55,86,110,121,143,162],"pose":[8,111],"estimation":[9],"using":[10,92],"convolutional":[11],"neural":[12],"networks":[13],"(CNNs)":[14],"can":[15,26],"learn":[16],"unlabelled":[17],"monocular":[18,44],"frames.":[19],"However,":[20],"three":[21],"problems":[22],"remain:":[23],"1)":[24],"CNNs":[25],"only":[27],"extract":[28,88],"local":[29],"features":[30],"due":[31],"to":[32,69,80,112,145],"the":[33,43,51,71,82,105,114,147,159,169,174],"limited":[34],"receptive":[35],"field,":[36],"2)":[37],"scale":[38,115,119],"ambiguity":[39,120],"is":[40,78,101,134,186],"inherent":[41],"in":[42,108,189],"task,":[45],"3)":[47],"illness":[48,152],"regions":[49],"violate":[50],"photometric":[52],"consistency":[53,99,107,138],"assumption":[54],"produce":[56],"large":[57],"errors.":[58],"We":[59],"propose":[60],"a":[61,75,93,123,131],"novel":[62],"framework,":[63],"ADPDepth,":[64],"with":[65],"corresponding":[66],"effective":[67],"strategies":[68],"ameliorate":[70],"above":[72],"problems.":[73],"First,":[74],"PCAtt":[76],"module":[77],"designed":[79],"capture":[81],"correlation":[83],"between":[84,116],"channels":[85],"efficiently":[87],"multiscale":[89],"spatial":[90],"information":[91],"multibranch":[94],"parallel":[95],"strategy.":[96],"Second,":[97],"depth-pose":[98,137],"loss":[100],"proposed":[102,175],"based":[103],"on":[104,158,166],"geometric":[106],"constrain":[113],"samples,":[117],"eliminate":[118],"obtain":[122],"globally":[124],"consistent":[125],"scale.":[126],"To":[127],"further":[128],"improve":[129],"performance,":[130],"cover":[132],"mask":[133],"derived":[135],"from":[136],"for":[139],"filtering":[140],"dynamic":[141],"objects":[142],"outliers":[144],"reduce":[146],"adverse":[148],"effects":[149],"of":[150,183],"these":[151],"regions.":[153],"Extensive":[154],"experiments":[155],"are":[156],"conducted":[157],"KITTI,":[160],"NYU-Depth":[161],"Make3D":[163],"datasets.":[164],"Based":[165],"public":[167],"benchmarks,":[168],"experimental":[170],"results":[171],"confirm":[172],"ADPDepth":[176],"framework":[177],"achieves":[178],"state-of-the-art":[179],"performance.":[180],"The":[181],"effectiveness":[182],"each":[184],"strategy":[185],"also":[187],"verified":[188],"subsequent":[190],"ablation":[191],"experiments.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}