{"id":"https://openalex.org/W4415481140","doi":"https://doi.org/10.1109/tpami.2025.3624589","title":"High-Resolution Open-Vocabulary Object 6D Pose Estimation","display_name":"High-Resolution Open-Vocabulary Object 6D Pose Estimation","publication_year":2025,"publication_date":"2025-10-23","ids":{"openalex":"https://openalex.org/W4415481140","doi":"https://doi.org/10.1109/tpami.2025.3624589","pmid":"https://pubmed.ncbi.nlm.nih.gov/41129457"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3624589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3624589","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":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/handle/20.500.14299/255231","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092574704","display_name":"Jaime Corsetti","orcid":"https://orcid.org/0009-0003-5454-1208"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Jaime Corsetti","raw_affiliation_strings":["Fondazione Bruno Kessler (FBK), Trento, Italy"],"raw_orcid":"https://orcid.org/0009-0003-5454-1208","affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler (FBK), Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064432821","display_name":"Davide Boscaini","orcid":"https://orcid.org/0000-0003-4887-2038"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Boscaini","raw_affiliation_strings":["Fondazione Bruno Kessler (FBK), Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4887-2038","affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler (FBK), Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080657058","display_name":"Francesco Giuliari","orcid":"https://orcid.org/0000-0003-2311-9517"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Giuliari","raw_affiliation_strings":["Fondazione Bruno Kessler (FBK), Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler (FBK), Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103187625","display_name":"Changjae Oh","orcid":"https://orcid.org/0000-0002-6522-2451"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Changjae Oh","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K","School of Electronic Engineering and Computer Science, Queen Mary University of London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-6522-2451","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004087827","display_name":"Andrea Cavallaro","orcid":"https://orcid.org/0000-0001-5086-7858"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andrea Cavallaro","raw_affiliation_strings":["EPFL, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067244774","display_name":"Fabio Poiesi","orcid":"https://orcid.org/0000-0002-9769-1279"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Poiesi","raw_affiliation_strings":["Fondazione Bruno Kessler (FBK), Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-9769-1279","affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler (FBK), Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25585207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"2","first_page":"2066","last_page":"2077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9674000144004822,"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":0.9674000144004822,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9139000177383423,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9115999937057495,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/pose","display_name":"Pose","score":0.7577999830245972},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6460000276565552},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6288999915122986},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5019999742507935},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4700999855995178},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4496999979019165},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.429500013589859},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.39399999380111694}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.82669997215271},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7577999830245972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751800000667572},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6460000276565552},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4975999891757965},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4496999979019165},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.429500013589859},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3686999976634979},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3125999867916107},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2971999943256378},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.28049999475479126}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2025.3624589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3624589","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:41129457","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41129457","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:infoscience.epfl.ch:20.500.14299/255231","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/255231","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"research article"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:20.500.14299/255231","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/255231","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"research article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"generalisation":[1],"to":[2,23,35,71,89],"unseen":[3,29,58,74,107],"objects":[4,108],"in":[5,76,129],"the":[6,68,73,77,132],"6D":[7,25],"pose":[8,26,51],"estimation":[9,27,52],"task":[10],"is":[11],"very":[12],"challenging.":[13],"While":[14],"Vision-Language":[15],"Models":[16],"(VLMs)":[17],"enable":[18],"using":[19],"natural":[20],"language":[21],"descriptions":[22],"support":[24],"of":[28,56,106],"objects,":[30],"these":[31],"solutions":[32],"underperform":[33],"compared":[34],"model-based":[36],"methods.":[37],"In":[38],"this":[39],"work":[40],"we":[41],"present":[42],"Horyon,":[43],"an":[44,57],"open-vocabulary":[45],"VLM-based":[46],"architecture":[47],"that":[48],"addresses":[49],"relative":[50],"between":[53],"two":[54],"scenes":[55,78],"object,":[59],"described":[60],"by":[61,127],"a":[62,100,103],"textual":[63,69],"prompt":[64,70],"only.":[65],"We":[66,95],"use":[67],"identify":[72],"object":[75],"and":[79,116],"then":[80],"obtain":[81],"high-resolution":[82],"multi-scale":[83],"features.":[84],"These":[85],"features":[86],"are":[87],"used":[88],"extract":[90],"cross-scene":[91],"matches":[92],"for":[93],"registration.":[94],"evaluate":[96],"our":[97],"model":[98],"on":[99,123],"benchmark":[101],"with":[102],"large":[104],"variety":[105],"across":[109],"four":[110],"datasets,":[111,125],"namely":[112],"REAL275,":[113],"Toyota-Light,":[114],"Linemod,":[115],"YCB-Video.":[117],"Our":[118],"method":[119],"achieves":[120],"state-of-the-art":[121],"performance":[122],"all":[124],"outperforming":[126],"12.6":[128],"Average":[130],"Recall":[131],"previous":[133],"best-performing":[134],"approach.":[135]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}
