{"id":"https://openalex.org/W4417201421","doi":"https://doi.org/10.1109/wacv61042.2026.00640","title":"OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding","display_name":"OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417201421","doi":"https://doi.org/10.1109/wacv61042.2026.00640"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.12614","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090075567","display_name":"Artem Moroz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ","SK"],"is_corresponding":false,"raw_author_name":"Artem Moroz","raw_affiliation_strings":["Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague","institution_ids":["https://openalex.org/I4210152232","https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104175145","display_name":"V\u00edt Zeman","orcid":"https://orcid.org/0009-0007-9304-9354"},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ","SK"],"is_corresponding":false,"raw_author_name":"V\u00edt Zeman","raw_affiliation_strings":["Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague","institution_ids":["https://openalex.org/I4210152232","https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119704493","display_name":"Martin Mik\u0161\u00edk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ","SK"],"is_corresponding":false,"raw_author_name":"Martin Mik\u0161\u00edk","raw_affiliation_strings":["Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague","institution_ids":["https://openalex.org/I4210152232","https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120761748","display_name":"Elizaveta Isianova","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ","SK"],"is_corresponding":false,"raw_author_name":"Elizaveta Isianova","raw_affiliation_strings":["Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague","institution_ids":["https://openalex.org/I4210152232","https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Miroslav David","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ","SK"],"is_corresponding":false,"raw_author_name":"Miroslav David","raw_affiliation_strings":["Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague","institution_ids":["https://openalex.org/I4210152232","https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085874366","display_name":"Pavel Burget","orcid":"https://orcid.org/0000-0002-4787-8182"},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ","SK"],"is_corresponding":false,"raw_author_name":"Pavel Burget","raw_affiliation_strings":["Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague","institution_ids":["https://openalex.org/I4210152232","https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092958510","display_name":"Varun Burde","orcid":"https://orcid.org/0000-0001-8317-6164"},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ","SK"],"is_corresponding":false,"raw_author_name":"Varun Burde","raw_affiliation_strings":["Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague","institution_ids":["https://openalex.org/I4210152232","https://openalex.org/I44504214"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6621","last_page":"6632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8955000042915344,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8955000042915344,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.019500000402331352,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.01860000006854534,"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/pose","display_name":"Pose","score":0.766700029373169},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.638700008392334},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.631600022315979},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5889999866485596},{"id":"https://openalex.org/keywords/onboarding","display_name":"Onboarding","score":0.5555999875068665},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.5415999889373779},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5235000252723694},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.450300008058548},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4262000024318695}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.766700029373169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7269999980926514},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.638700008392334},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.631600022315979},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5648000240325928},{"id":"https://openalex.org/C2779185108","wikidata":"https://www.wikidata.org/wiki/Q7091744","display_name":"Onboarding","level":2,"score":0.5555999875068665},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.5415999889373779},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5235000252723694},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.450300008058548},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.38260000944137573},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.31279999017715454},{"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/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.12614","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.12614","pdf_url":"https://arxiv.org/pdf/2511.12614","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.12614","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.12614","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.12614","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.12614","pdf_url":"https://arxiv.org/pdf/2511.12614","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,15,43,52,85,90,146],"unified,":[3],"end-to-end":[4],"framework":[5],"that":[6,26,88],"seamlessly":[7],"integrates":[8],"object":[9,28,101],"detection":[10],"and":[11,109,151,160],"pose":[12,71],"estimation":[13,72],"with":[14,22,113],"versatile":[16],"onboarding":[17,24],"process.":[18],"Our":[19],"pipeline":[20],"begins":[21],"an":[23,100],"stage":[25],"generates":[27],"representations":[29],"from":[30,48],"either":[31],"traditional":[32],"3D":[33,115],"CAD":[34],"models":[35],"or,":[36],"in":[37,157],"their":[38],"absence,":[39],"by":[40,103],"rapidly":[41],"reconstructing":[42],"high-fidelity":[44],"neural":[45],"representation":[46,102],"(NeRF)":[47],"multi-view":[49],"images.":[50],"Given":[51],"test":[53],"image,":[54],"our":[55,69,142],"system":[56,144],"first":[57],"employs":[58],"the":[59,76,133,138],"CNOS":[60],"detector":[61],"to":[62,131],"localize":[63],"target":[64],"objects.":[65],"For":[66],"each":[67],"detection,":[68],"novel":[70],"module,":[73],"OPFormer,":[74],"infers":[75],"precise":[77],"6D":[78],"pose.":[79,135],"The":[80],"core":[81],"of":[82],"OPFormer":[83],"is":[84],"transformer-based":[86],"architecture":[87],"leverages":[89],"foundation":[91],"model":[92],"for":[93],"robust":[94,128],"feature":[95],"extraction.":[96],"It":[97],"uniquely":[98],"learns":[99],"jointly":[104],"encoding":[105],"multiple":[106],"template":[107],"views":[108],"enriches":[110],"these":[111],"features":[112],"explicit":[114],"geometric":[116],"priors":[117],"using":[118],"Normalized":[119],"Object":[120],"Coordinate":[121],"Space":[122],"(NOCS).":[123],"A":[124],"decoder":[125],"then":[126],"establishes":[127],"2D3D":[129],"correspondences":[130],"determine":[132],"final":[134],"Evaluated":[136],"on":[137],"challenging":[139],"BOP":[140],"benchmarks,":[141],"integrated":[143],"demonstrates":[145],"strong":[147],"balance":[148],"between":[149],"accuracy":[150],"efficiency,":[152],"showcasing":[153],"its":[154],"practical":[155],"applicability":[156],"both":[158],"model-based":[159],"model-free":[161],"scenarios.":[162]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-19T00:00:00"}