{"id":"https://openalex.org/W4414758360","doi":"https://doi.org/10.1109/iccv51701.2025.00697","title":"3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection","display_name":"3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414758360","doi":"https://doi.org/10.1109/iccv51701.2025.00697"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.23567","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045674000","display_name":"Yung-Hsu Yang","orcid":"https://orcid.org/0000-0003-0044-515X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yung-Hsu Yang","raw_affiliation_strings":["ETH Zürich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077478426","display_name":"Luigi Piccinelli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luigi Piccinelli","raw_affiliation_strings":["ETH Zürich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mattia Segu","raw_affiliation_strings":["ETH Zürich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406609","display_name":"Siyuan Li","orcid":"https://orcid.org/0000-0001-6806-2468"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyuan Li","raw_affiliation_strings":["ETH Zürich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101524226","display_name":"Rui Huang","orcid":"https://orcid.org/0000-0001-9305-2915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Huang","raw_affiliation_strings":["ETH Zürich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102678888","display_name":"Yuqian Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuqian Fu","raw_affiliation_strings":["INSAIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSAIT","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021908609","display_name":"Marc Pollefeys","orcid":"https://orcid.org/0000-0003-2448-2318"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Pollefeys","raw_affiliation_strings":["ETH Zürich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012921430","display_name":"Hermann Blum","orcid":"https://orcid.org/0000-0002-1713-7877"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hermann Blum","raw_affiliation_strings":["ETH Zürich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062464940","display_name":"Zuria Bauer","orcid":"https://orcid.org/0000-0001-8447-2344"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuria Bauer","raw_affiliation_strings":["ETH Zürich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5045674000"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36237177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7429","last_page":"7439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9004999995231628,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9004999995231628,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/monocular","display_name":"Monocular","score":0.7850000262260437},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7042999863624573},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5630999803543091},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5268999934196472},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5011000037193298},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.47189998626708984},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4275999963283539},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8093000054359436},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7850000262260437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7487000226974487},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7042999863624573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6916000247001648},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5268999934196472},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.47189998626708984},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4275999963283539},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.35690000653266907},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.32510000467300415},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2549999952316284}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.23567","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.23567","pdf_url":"https://arxiv.org/pdf/2507.23567","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"},{"id":"doi:10.48550/arxiv.2507.23567","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.23567","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.23567","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.23567","pdf_url":"https://arxiv.org/pdf/2507.23567","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/F4320331518","display_name":"Centro Svizzero di Calcolo Scientifico","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Monocular":[0,71],"3D":[1,58,70,85,90,102,122],"object":[2,33,44,59,112],"detection":[3,60,83],"is":[4],"valuable":[5],"for":[6,98,121,137],"various":[7],"applications":[8,37],"such":[9],"as":[10],"robotics":[11],"and":[12,24,42,65,101,117,150,158,164],"AR/VR.":[13],"Existing":[14],"methods":[15],"are":[16,166],"confined":[17],"to":[18,49,78,104,154],"closed-set":[19,147],"settings,":[20],"where":[21],"the":[22,29,67,80,111,119,133],"training":[23,97],"testing":[25],"sets":[26],"consist":[27],"of":[28],"same":[30],"scenes":[31],"and/or":[32],"categories.":[34],"However,":[35],"real-world":[36],"often":[38],"introduce":[39,66],"new":[40,160],"environments":[41],"novel":[43],"categories,":[45],"posing":[46],"a":[47],"challenge":[48],"these":[50],"methods.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,131],"address":[56],"monocular":[57],"in":[61],"an":[62],"open-set":[63,81,151],"setting":[64],"first":[68],"end-to-end":[69,95],"Open-set":[72],"Object":[73],"Detector":[74],"(3D-MOOD).":[75],"We":[76,109,142],"propose":[77],"lift":[79],"2D":[82,100],"into":[84],"space":[86,136],"through":[87],"our":[88],"designed":[89],"bounding":[91],"box":[92],"head,":[93],"enabling":[94],"joint":[96],"both":[99,146],"tasks":[103],"yield":[105],"better":[106],"overall":[107],"performance.":[108],"condition":[110],"queries":[113],"with":[114],"geometry":[115],"prior":[116],"overcome":[118],"generalization":[120],"estimation":[123],"across":[124],"diverse":[125],"scenes.":[126],"To":[127],"further":[128],"improve":[129],"performance,":[130],"design":[132],"canonical":[134],"image":[135],"more":[138],"efficient":[139],"cross-dataset":[140],"training.":[141],"evaluate":[143],"3D-MOOD":[144],"on":[145],"settings":[148,152],"(Omni3D)":[149],"(Omni3D":[153],"Argoverse":[155],"2,":[156],"ScanNet),":[157],"achieve":[159],"state-of-the-art":[161],"results.":[162],"Code":[163],"models":[165],"available":[167],"at":[168],"royyang0714.github.io/3D-MOOD.":[169]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}