{"id":"https://openalex.org/W4360584429","doi":"https://doi.org/10.1109/tcsvt.2023.3260310","title":"METER: A Mobile Vision Transformer Architecture for Monocular Depth Estimation","display_name":"METER: A Mobile Vision Transformer Architecture for Monocular Depth Estimation","publication_year":2023,"publication_date":"2023-03-22","ids":{"openalex":"https://openalex.org/W4360584429","doi":"https://doi.org/10.1109/tcsvt.2023.3260310"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3260310","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3260310","pdf_url":"https://ieeexplore.ieee.org/ielx7/76/4358651/10078346.pdf","source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/76/4358651/10078346.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010287961","display_name":"Lorenzo Papa","orcid":"https://orcid.org/0000-0002-9393-5248"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Papa","raw_affiliation_strings":["Department of Computer, Control, and Management Engineering, Sapienza University of Rome, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-9393-5248","affiliations":[{"raw_affiliation_string":"Department of Computer, Control, and Management Engineering, Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062555637","display_name":"Paolo Russo","orcid":"https://orcid.org/0000-0002-1886-3491"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Russo","raw_affiliation_strings":["Department of Computer, Control, and Management Engineering, Sapienza University of Rome, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1886-3491","affiliations":[{"raw_affiliation_string":"Department of Computer, Control, and Management Engineering, Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030121038","display_name":"Irene Amerini","orcid":"https://orcid.org/0000-0002-6461-1391"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Irene Amerini","raw_affiliation_strings":["Department of Computer, Control, and Management Engineering, Sapienza University of Rome, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6461-1391","affiliations":[{"raw_affiliation_string":"Department of Computer, Control, and Management Engineering, Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3788,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.958019,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"33","issue":"10","first_page":"5882","last_page":"5893"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":1.0,"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":1.0,"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":0.9993000030517578,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7945576906204224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6014143228530884},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.597054123878479},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5155367851257324},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4918546676635742},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4688127040863037},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.4507826864719391},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4368535876274109},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43444395065307617},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.42619168758392334},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4167421758174896},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.41487106680870056},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12122243642807007}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945576906204224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6014143228530884},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.597054123878479},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5155367851257324},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4918546676635742},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4688127040863037},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.4507826864719391},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4368535876274109},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43444395065307617},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.42619168758392334},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4167421758174896},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.41487106680870056},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12122243642807007},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcsvt.2023.3260310","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3260310","pdf_url":"https://ieeexplore.ieee.org/ielx7/76/4358651/10078346.pdf","source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2403.08368","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.08368","pdf_url":"https://arxiv.org/pdf/2403.08368","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:iris.uniroma1.it:11573/1675431","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1675431","pdf_url":"https://iris.uniroma1.it/bitstream/11573/1675431/3/Papa_Meter_2023.pdf","source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/tcsvt.2023.3260310","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3260310","pdf_url":"https://ieeexplore.ieee.org/ielx7/76/4358651/10078346.pdf","source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322510","display_name":"Sapienza Universit\u00e0 di Roma","ror":"https://ror.org/02be6w209"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4360584429.pdf","grobid_xml":"https://content.openalex.org/works/W4360584429.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1522301498","https://openalex.org/W2081900960","https://openalex.org/W2115579991","https://openalex.org/W2133665775","https://openalex.org/W2194775991","https://openalex.org/W2520707372","https://openalex.org/W2531409750","https://openalex.org/W2787091153","https://openalex.org/W2961343177","https://openalex.org/W2962741876","https://openalex.org/W2962928205","https://openalex.org/W2963163009","https://openalex.org/W2963267406","https://openalex.org/W2963446712","https://openalex.org/W2963911235","https://openalex.org/W2964052474","https://openalex.org/W2967115342","https://openalex.org/W2967733054","https://openalex.org/W3025045095","https://openalex.org/W3118453581","https://openalex.org/W3118635606","https://openalex.org/W3128121047","https://openalex.org/W3140854437","https://openalex.org/W3173727695","https://openalex.org/W3175059103","https://openalex.org/W3186318242","https://openalex.org/W3190492058","https://openalex.org/W3200000156","https://openalex.org/W3212645988","https://openalex.org/W4214520160","https://openalex.org/W4225949693","https://openalex.org/W4226191818","https://openalex.org/W4226254592","https://openalex.org/W4286910290","https://openalex.org/W4289082871","https://openalex.org/W4295934562","https://openalex.org/W4297775537","https://openalex.org/W4385245566","https://openalex.org/W4386723894","https://openalex.org/W6631190155","https://openalex.org/W6685261749","https://openalex.org/W6737664043","https://openalex.org/W6757246177","https://openalex.org/W6798891274","https://openalex.org/W6802648153","https://openalex.org/W6810242703","https://openalex.org/W6810661541","https://openalex.org/W6811234694"],"related_works":["https://openalex.org/W2085033728","https://openalex.org/W4285411112","https://openalex.org/W2171299904","https://openalex.org/W1647606319","https://openalex.org/W200819717","https://openalex.org/W4390494008","https://openalex.org/W2053596378","https://openalex.org/W2922442631","https://openalex.org/W2168523118","https://openalex.org/W2032269556"],"abstract_inverted_index":{"Depth":[0,229],"estimation":[1,26,70,196],"is":[2],"a":[3,76,81,147,180,189,203],"fundamental":[4],"knowledge":[5],"for":[6,24,108],"autonomous":[7],"systems":[8,133],"that":[9,99],"need":[10],"to":[11,35,53,193,208],"assess":[12],"their":[13,65],"own":[14],"state":[15,156],"and":[16,57,103,141,161,174,197,202,231],"perceive":[17],"the":[18,36,44,54,88,122,158,167,210,222,226,232],"surrounding":[19],"environment.":[20],"Deep":[21],"learning":[22],"algorithms":[23],"depth":[25,48,69,78],"have":[27,63],"gained":[28],"significant":[29],"interest":[30],"in":[31,42,74,117,127],"recent":[32],"years,":[33],"owing":[34],"potential":[37],"benefits":[38],"of":[39,46,59,87,124,154,157,183,187,199],"this":[40,118],"methodology":[41],"overcoming":[43],"limitations":[45],"active":[47],"sensing":[49],"systems.":[50],"Moreover,":[51],"due":[52],"low":[55,162],"cost":[56],"size":[58],"monocular":[60,68],"cameras,":[61],"researchers":[62],"focused":[64],"attention":[66],"on":[67,94,111,129,166],"(MDE),":[71],"which":[72],"consists":[73],"estimating":[75],"dense":[77],"map":[79],"from":[80],"single":[82],"RGB":[83],"video":[84],"frame.":[85],"State":[86],"art":[89,159],"MDE":[90,128],"models":[91],"typically":[92],"rely":[93],"vision":[95,150],"transformers":[96],"(ViT)":[97],"architectures":[98],"are":[100,134],"highly":[101],"deep":[102],"complex,":[104],"making":[105],"them":[106],"unsuitable":[107],"fast":[109],"inference":[110,164],"devices":[112],"with":[113],"hardware":[114],"constraints.":[115],"Purposely,":[116],"paper,":[119],"we":[120],"address":[121],"problem":[123],"exploiting":[125],"ViT":[126],"embedded":[130,169],"devices.":[131],"Those":[132],"usually":[135],"characterized":[136],"by":[137],"limited":[138],"memory":[139],"capabilities":[140],"low-power":[142],"CPU/GPU.":[143],"We":[144,178],"propose":[145],"METER,":[146,188],"novel":[148,190],"lightweight":[149,219],"transformer":[151],"architecture":[152],"capable":[153],"achieving":[155],"estimations":[160],"latency":[163],"performances":[165],"considered":[168],"hardwares:":[170],"NVIDIA":[171,175],"Jetson":[172,176],"TX1":[173],"Nano.":[177],"provide":[179],"solution":[181],"consisting":[182],"three":[184],"alternative":[185],"configurations":[186],"loss":[191],"function":[192],"balance":[194],"pixel":[195],"reconstruction":[198],"image":[200],"details,":[201],"new":[204],"data":[205],"augmentation":[206],"strategy":[207],"improve":[209],"overall":[211],"final":[212],"predictions.":[213],"The":[214],"proposed":[215],"method":[216],"outperforms":[217],"previous":[218],"works":[220],"over":[221],"two":[223],"benchmark":[224],"datasets:":[225],"indoor":[227],"NYU":[228],"v2":[230],"outdoor":[233],"KITTI.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-03-24T00:00:00"}