{"id":"https://openalex.org/W4400611523","doi":"https://doi.org/10.1109/tcsvt.2026.3667405","title":"ScaleDepth: Decomposing Metric Depth Estimation Into Semantic-Aware Scale Prediction and Adaptive Relative Depth Estimation","display_name":"ScaleDepth: Decomposing Metric Depth Estimation Into Semantic-Aware Scale Prediction and Adaptive Relative Depth Estimation","publication_year":2026,"publication_date":"2026-02-23","ids":{"openalex":"https://openalex.org/W4400611523","doi":"https://doi.org/10.1109/tcsvt.2026.3667405"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2026.3667405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3667405","pdf_url":null,"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":null,"license_id":null,"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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.08187","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101586136","display_name":"Ruijie Zhu","orcid":"https://orcid.org/0000-0001-6092-0712"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruijie Zhu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6092-0712","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chuxin Wang","orcid":"https://orcid.org/0000-0003-1431-7677"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuxin Wang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1431-7677","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076263241","display_name":"Ziyang Song","orcid":"https://orcid.org/0009-0009-6348-8713"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Song","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0009-0009-6348-8713","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li Liu","orcid":"https://orcid.org/0009-0004-3280-8490"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0009-0004-3280-8490","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianfeng He","orcid":"https://orcid.org/0000-0002-7700-788X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng He","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7700-788X","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiacheng Deng","orcid":"https://orcid.org/0000-0003-2838-0378"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacheng Deng","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2838-0378","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianzhu Zhang","orcid":"https://orcid.org/0000-0003-1856-9564"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzhu Zhang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1856-9564","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1151-1792","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.00312123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"36","issue":"7","first_page":"9547","last_page":"9560"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9736999869346619,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9736999869346619,"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/estimation","display_name":"Estimation","score":0.8265471458435059},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6845519542694092},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6286718845367432},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.48935073614120483},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.46766483783721924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3724631071090698},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.2962019443511963},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.16388875246047974},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.12934499979019165}],"concepts":[{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.8265471458435059},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6845519542694092},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6286718845367432},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.48935073614120483},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46766483783721924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3724631071090698},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2962019443511963},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.16388875246047974},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.12934499979019165},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tcsvt.2026.3667405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3667405","pdf_url":null,"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":null,"license_id":null,"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:2407.08187","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.08187","pdf_url":"https://arxiv.org/pdf/2407.08187","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2407.08187","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2407.08187","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.08187","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.08187","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.08187","pdf_url":"https://arxiv.org/pdf/2407.08187","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4500403938","display_name":null,"funder_award_id":"42595545","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6447223638","display_name":null,"funder_award_id":"U25A20536","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2600246793","https://openalex.org/W4238204885"],"abstract_inverted_index":{"Estimating":[0],"the":[1,8,52,108,119,127,133,163,167,172],"depth":[2,18,21,40,56,67,75,81,96,135,143,150,168],"map":[3],"of":[4,48,54,118,137],"an":[5,93],"image":[6,139],"in":[7,35,158,183],"wild":[9],"is":[10],"a":[11,64,86,141,159],"challenging":[12],"visual":[13],"task.":[14],"Compared":[15],"to":[16,27,121,165],"relative":[17,49,80,95,134],"estimation,":[19],"metric":[20,55,74,149],"estimation":[22,41,68,97,151],"attracts":[23],"more":[24],"attention":[25],"due":[26],"its":[28],"practical":[29],"physical":[30],"significance":[31],"and":[32,79,82,92,115,155,187],"critical":[33],"applications":[34],"real-life":[36],"scenarios.":[37],"However,":[38],"existing":[39],"methods":[42],"typically":[43],"focus":[44],"only":[45],"on":[46],"generalization":[47],"depth,":[50],"neglecting":[51],"importance":[53],"generalization.":[57],"To":[58],"address":[59],"this":[60],"challenge,":[61],"we":[62],"propose":[63],"novel":[65],"monocular":[66],"method":[69,147,179],"called":[70],"ScaleDepth.":[71],"It":[72],"decomposes":[73],"into":[76],"scene":[77,124],"scale":[78,88],"predicts":[83],"them":[84],"through":[85],"semantic-aware":[87],"prediction":[89],"(SASP)":[90],"module":[91,110,129],"adaptive":[94],"(ARDE)":[98],"module,":[99],"respectively.":[100],"Our":[101],"proposed":[102],"approach":[103],"has":[104],"several":[105],"merits.":[106],"First,":[107],"SASP":[109],"can":[111,130],"implicitly":[112],"combine":[113],"structural":[114],"semantic":[116],"features":[117],"images":[120],"predict":[122],"precise":[123],"scales.":[125],"Second,":[126],"ARDE":[128],"adaptively":[131],"estimate":[132],"distribution":[136],"each":[138],"within":[140],"normalized":[142],"space.":[144],"Third,":[145],"our":[146,178],"achieves":[148,180],"for":[152],"both":[153],"indoor":[154],"outdoor":[156],"scenes":[157],"unified":[160],"framework,":[161],"without":[162],"need":[164],"set":[166],"range":[169],"or":[170],"fine-tune":[171],"model.":[173],"Extensive":[174],"experiments":[175],"demonstrate":[176],"that":[177],"competitive":[181],"performance":[182],"indoor,":[184],"outdoor,":[185],"unconfined,":[186],"unseen":[188],"scenes.":[189],"Project":[190],"page:":[191],"https://ruijiezhu94.github.io/ScaleDepth.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2024-07-14T00:00:00"}
