{"id":"https://openalex.org/W4403792394","doi":"https://doi.org/10.1145/3664647.3681405","title":"SM <sup>4</sup> Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One Model","display_name":"SM <sup>4</sup> Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One Model","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792394","doi":"https://doi.org/10.1145/3664647.3681405"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681405","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5031679490","display_name":"Yihao Liu","orcid":"https://orcid.org/0000-0001-6350-2073"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihao Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6350-2073","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058354365","display_name":"Feng Xue","orcid":"https://orcid.org/0000-0002-4101-3401"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Feng Xue","raw_affiliation_strings":["University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-4101-3401","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082092902","display_name":"Anlong Ming","orcid":"https://orcid.org/0000-0003-2952-7757"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anlong Ming","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2952-7757","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingshuai Zhao","orcid":"https://orcid.org/0009-0001-7846-6391"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingshuai Zhao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-7846-6391","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710713","display_name":"Huad\u00f3ng Ma","orcid":"https://orcid.org/0000-0002-7199-5047"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huadong Ma","raw_affiliation_strings":["Beijing University of Post and Telecommunication, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7199-5047","affiliations":[{"raw_affiliation_string":"Beijing University of Post and Telecommunication, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027171279","display_name":"Nicu Sebe","orcid":"https://orcid.org/0000-0002-6597-7248"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicu Sebe","raw_affiliation_strings":["University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6597-7248","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3469","last_page":"3478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9998000264167786,"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":0.9998000264167786,"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/T10638","display_name":"Optical measurement and interference techniques","score":0.9987999796867371,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/metric","display_name":"Metric (unit)","score":0.716219961643219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6337924003601074},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5986809134483337},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5781909227371216},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.563976526260376},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.45136263966560364},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10417884588241577}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.716219961643219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6337924003601074},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5986809134483337},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5781909227371216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.563976526260376},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.45136263966560364},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10417884588241577},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681405","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unitn.it:11572/439531","is_oa":false,"landing_page_url":"https://hdl.handle.net/11572/439531","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1923184257","https://openalex.org/W2340897893","https://openalex.org/W2493502717","https://openalex.org/W2560722161","https://openalex.org/W2594519801","https://openalex.org/W2604213426","https://openalex.org/W2740729727","https://openalex.org/W2741885505","https://openalex.org/W2781181706","https://openalex.org/W2897399830","https://openalex.org/W2897840891","https://openalex.org/W2944744832","https://openalex.org/W2963292632","https://openalex.org/W2963760790","https://openalex.org/W2981402926","https://openalex.org/W3034604951","https://openalex.org/W3035574168","https://openalex.org/W3081167590","https://openalex.org/W3090787154","https://openalex.org/W3092693966","https://openalex.org/W3129975431","https://openalex.org/W3205015613","https://openalex.org/W3206676575","https://openalex.org/W3207182648","https://openalex.org/W3207807635","https://openalex.org/W4206342640","https://openalex.org/W4214520160","https://openalex.org/W4221148818","https://openalex.org/W4283838088","https://openalex.org/W4290713684","https://openalex.org/W4297683907","https://openalex.org/W4297845938","https://openalex.org/W4302275500","https://openalex.org/W4312311094","https://openalex.org/W4312871721","https://openalex.org/W4322616103","https://openalex.org/W4386065367","https://openalex.org/W4386081231","https://openalex.org/W4386180266","https://openalex.org/W4387607657","https://openalex.org/W4387967982","https://openalex.org/W4387968096","https://openalex.org/W4387968192","https://openalex.org/W4387968702","https://openalex.org/W4390871919","https://openalex.org/W4390872862","https://openalex.org/W4390873054","https://openalex.org/W6821011379"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0],"the":[1,17,48,123,126,162,166,189,215],"last":[2],"year,":[3],"universal":[4],"monocular":[5],"metric":[6,112,128,167],"depth":[7,104,119,136,183,190],"estimation":[8],"(universal":[9],"MMDE)":[10],"has":[11],"gained":[12],"considerable":[13],"attention,":[14],"serving":[15],"as":[16,25],"foundation":[18],"model":[19,82],"for":[20,68,86],"various":[21,195],"multimedia":[22],"tasks,":[23],"such":[24],"video":[26],"and":[27,45,74,89,97,130,147,192,197,225],"image":[28],"editing.":[29],"Nonetheless,":[30],"current":[31],"approaches":[32],"face":[33],"challenges":[34],"in":[35],"maintaining":[36,220],"consistent":[37,103,221],"accuracy":[38,191,222],"across":[39,105,194,223],"diverse":[40,106],"scenes":[41,139],"without":[42,92],"scene-specific":[43],"parameters":[44],"pre-training,":[46],"hindering":[47],"practicality":[49],"of":[50,64,66,125,138,158],"MMDE.":[51],"Furthermore,":[52],"these":[53],"methods":[54],"rely":[55],"on":[56,153,201,214],"extensive":[57,94],"datasets":[58],"comprising":[59],"millions,":[60,65],"if":[61],"not":[62],"tens":[63],"data":[67,96],"training,":[69],"leading":[70],"to":[71,101,134,150,175,187],"significant":[72],"time":[73],"hardware":[75],"expenses.":[76],"This":[77],"paper":[78],"presents":[79],"SM4Depth,":[80],"a":[81,110,145,202],"that":[83],"seamlessly":[84],"works":[85],"both":[87],"indoor":[88,196],"outdoor":[90,198],"scenes,":[91,107],"needing":[93],"training":[95,155],"GPU":[98,204],"clusters.":[99],"Firstly,":[100],"obtain":[102],"we":[108,143,179],"propose":[109,144],"novel":[111],"scale":[113],"modeling,":[114],"i.e.,":[115],"variation-":[116],"based":[117],"unnormalized":[118],"bins.":[120],"It":[121],"reduces":[122],"ambiguity":[124],"conventional":[127],"bins":[129,168],"enables":[131],"better":[132],"adaptation":[133],"large":[135],"gaps":[137],"during":[140],"training.":[141],"Secondly,":[142],"''divide":[146],"conquer''":[148],"solution":[149,164,173],"reduce":[151,176],"reliance":[152],"massive":[154],"data.":[156],"Instead":[157],"estimating":[159],"directly":[160],"from":[161,171],"vast":[163],"space,":[165],"are":[169],"estimated":[170],"multiple":[172],"sub-spaces":[174],"complexity.":[177],"Additionally,":[178],"introduce":[180],"an":[181],"uncut":[182],"dataset,":[184],"BUPT":[185],"Depth,":[186],"evaluate":[188],"consistency":[193],"scenes.":[199],"Trained":[200],"consumer-grade":[203],"using":[205],"just":[206],"150K":[207],"RGB-D":[208],"pairs,":[209],"SM4Depth":[210],"achieves":[211],"outstanding":[212],"performance":[213],"most":[216],"never-before-seen":[217],"datasets,":[218],"especially":[219],"indoors":[224],"outdoors.":[226],"The":[227],"code":[228],"can":[229],"be":[230],"found":[231],"here.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}