{"id":"https://openalex.org/W4415821356","doi":"https://doi.org/10.1109/tpami.2025.3628473","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","display_name":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","publication_year":2025,"publication_date":"2025-11-03","ids":{"openalex":"https://openalex.org/W4415821356","doi":"https://doi.org/10.1109/tpami.2025.3628473","pmid":"https://pubmed.ncbi.nlm.nih.gov/41182939"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3628473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3628473","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.20110","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003363172","display_name":"Luigi Piccinelli","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Luigi Piccinelli","raw_affiliation_strings":["ETH Zürich, Zurich, Switzerland","ETH Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zürich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Zürich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058481699","display_name":"Christos Sakaridis","orcid":"https://orcid.org/0000-0003-1127-8887"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christos Sakaridis","raw_affiliation_strings":["ETH Zürich, Zurich, Switzerland","ETH Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zürich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Zürich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045674000","display_name":"Yung-Hsu Yang","orcid":"https://orcid.org/0000-0003-0044-515X"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yung-Hsu Yang","raw_affiliation_strings":["ETH Zürich, Zurich, Switzerland","ETH Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zürich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Zürich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025696769","display_name":"Mattia Seg\u00f9","orcid":"https://orcid.org/0000-0002-9107-531X"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mattia Segu","raw_affiliation_strings":["ETH Zürich, Zurich, Switzerland","ETH Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zürich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Zürich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406609","display_name":"Siyuan Li","orcid":"https://orcid.org/0000-0001-6806-2468"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Siyuan Li","raw_affiliation_strings":["ETH Zürich, Zurich, Switzerland","ETH Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zürich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Zürich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013360054","display_name":"Wim Abbeloos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120547","display_name":"Toyota Motor Corporation (Belgium)","ror":"https://ror.org/023g86t37","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210120547","https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Wim Abbeloos","raw_affiliation_strings":["Toyota Motor Europe, Brussels, Belgium","Toyota Motor Europe, Belgium"],"affiliations":[{"raw_affiliation_string":"Toyota Motor Europe, Brussels, Belgium","institution_ids":["https://openalex.org/I4210120547"]},{"raw_affiliation_string":"Toyota Motor Europe, Belgium","institution_ids":["https://openalex.org/I4210120547"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001254143","display_name":"Luc Van Gool","orcid":"https://orcid.org/0000-0002-3445-5711"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luc Van Gool","raw_affiliation_strings":["ETH Zürich, Zurich, Switzerland","ETH Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zürich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Zürich, Switzerland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5003363172"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":13.0565,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.98939127,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"48","issue":"3","first_page":"2354","last_page":"2367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9341999888420105,"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":0.9341999888420105,"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":0.024800000712275505,"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":0.007699999958276749,"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/metric","display_name":"Metric (unit)","score":0.7498000264167786},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6682999730110168},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5953999757766724},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5759999752044678},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5467000007629395},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3977000117301941},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.37380000948905945},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3294999897480011}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7498000264167786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7091000080108643},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6682999730110168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6129999756813049},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5953999757766724},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5927000045776367},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5759999752044678},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5467000007629395},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37380000948905945},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2793999910354614},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25870001316070557}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2025.3628473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3628473","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41182939","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41182939","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2502.20110","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.20110","pdf_url":"https://arxiv.org/pdf/2502.20110","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.20110","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.20110","pdf_url":"https://arxiv.org/pdf/2502.20110","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335507","display_name":"Toyota Motor Europe","ror":"https://ror.org/023g86t37"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"monocular":[1],"metric":[2,61,79,169],"depth":[3,116,130,146,170,195],"estimation":[4],"(MMDE)":[5],"is":[6,25],"crucial":[7],"to":[8,27,34,36,114],"solving":[9],"downstream":[10,187],"tasks":[11,188],"in":[12,40,167,197],"3D":[13,62,80],"perception":[14],"and":[15,97,129,163,175,180,206,211],"modeling.":[16],"However,":[17],"the":[18,41,72,83,127,142,161,168,203],"remarkable":[19],"accuracy":[20],"of":[21,43,59,144,165,208],"recent":[22],"MMDE":[23,74,99],"methods":[24,32],"confined":[26],"their":[28,49],"training":[29],"domains.":[30,69],"These":[31],"fail":[33],"generalize":[35],"unseen":[37],"domains":[38],"even":[39],"presence":[42],"moderate":[44],"domain":[45],"gaps,":[46],"which":[47,125,159,185],"hinders":[48],"practical":[50],"applicability.":[51],"We":[52],"propose":[53,135],"a":[54,95,105,110,121,136,155,172,198],"new":[55,156],"model,":[56],"UniDepthV2,":[57],"capable":[58],"reconstructing":[60],"scenes":[63],"from":[64,71,82],"solely":[65],"single":[66],"images":[67],"across":[68],"Departing":[70],"existing":[73],"paradigm,":[75],"UniDepthV2":[76,103,148],"directly":[77],"predicts":[78],"points":[81],"input":[84],"image":[85],"at":[86],"inference":[87],"time":[88],"without":[89],"any":[90],"additional":[91,182],"information,":[92],"striving":[93],"for":[94],"universal":[96],"flexible":[98],"solution.":[100],"In":[101,132],"particular,":[102],"implements":[104],"self-promptable":[106],"camera":[107,112,128],"module":[108],"predicting":[109],"dense":[111],"representation":[113],"condition":[115],"features.":[117,147],"Our":[118],"model":[119,153],"exploits":[120],"pseudo-spherical":[122],"output":[123,184],"representation,":[124],"disentangles":[126],"representations.":[131],"addition,":[133],"we":[134],"geometric":[137],"invariance":[138,143],"loss":[139,158],"that":[140],"promotes":[141],"camera-prompted":[145],"improves":[149],"its":[150],"predecessor":[151],"UniDepth":[152],"via":[154],"edge-guided":[157],"enhances":[160],"localization":[162],"sharpness":[164],"edges":[166],"outputs,":[171],"revisited,":[173],"simplified":[174],"more":[176],"efficient":[177],"architectural":[178],"design,":[179],"an":[181],"uncertainty-level":[183],"enables":[186],"requiring":[189],"confidence.":[190],"Thorough":[191],"evaluations":[192],"on":[193],"ten":[194],"datasets":[196],"zero-shot":[199],"regime":[200],"consistently":[201],"demonstrate":[202],"superior":[204],"performance":[205],"generalization":[207],"UniDepthV2.":[209],"Code":[210],"models":[212],"are":[213],"available":[214],"at:":[215],"github.com/lpiccinelli-eth/UniDepth.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-11-03T00:00:00"}