{"id":"https://openalex.org/W4404469289","doi":"https://doi.org/10.1109/lra.2024.3501677","title":"Simultaneous Geometry and Pose Estimation of Held Objects Via 3D Foundation Models","display_name":"Simultaneous Geometry and Pose Estimation of Held Objects Via 3D Foundation Models","publication_year":2024,"publication_date":"2024-11-18","ids":{"openalex":"https://openalex.org/W4404469289","doi":"https://doi.org/10.1109/lra.2024.3501677"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3501677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3501677","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077799676","display_name":"Weiming Zhi","orcid":"https://orcid.org/0000-0002-0958-6656"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiming Zhi","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Robotics Institute, Carnegie Mellon University, USA"],"raw_orcid":"https://orcid.org/0000-0002-0958-6656","affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029366297","display_name":"Haozhan Tang","orcid":"https://orcid.org/0000-0001-6719-846X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haozhan Tang","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Robotics Institute, Carnegie Mellon University, USA"],"raw_orcid":"https://orcid.org/0000-0001-6719-846X","affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437441","display_name":"Tianyi Zhang","orcid":"https://orcid.org/0000-0001-6758-7203"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Zhang","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Robotics Institute, Carnegie Mellon University, USA"],"raw_orcid":"https://orcid.org/0000-0001-6758-7203","affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089990642","display_name":"Matthew Johnson\u2010Roberson","orcid":"https://orcid.org/0000-0002-0506-907X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Johnson-Roberson","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Robotics Institute, Carnegie Mellon University, USA"],"raw_orcid":"https://orcid.org/0000-0002-0506-907X","affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.5146,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57442369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"9","issue":"12","first_page":"11818","last_page":"11825"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.9861000180244446,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/foundation","display_name":"Foundation (evidence)","score":0.8015486598014832},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.5642930865287781},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5027596950531006},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.4810509979724884},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4577660858631134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4407520294189453},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33179137110710144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2911302447319031},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22634348273277283},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.19967412948608398},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.12222093343734741},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06333789229393005}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.8015486598014832},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.5642930865287781},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5027596950531006},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.4810509979724884},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4577660858631134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4407520294189453},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33179137110710144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2911302447319031},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22634348273277283},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.19967412948608398},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.12222093343734741},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06333789229393005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3501677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3501677","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2000359213","https://openalex.org/W2094801294","https://openalex.org/W2158057652","https://openalex.org/W2471962767","https://openalex.org/W2962793285","https://openalex.org/W2963209451","https://openalex.org/W2963892972","https://openalex.org/W2968355674","https://openalex.org/W3034986117","https://openalex.org/W3092774272","https://openalex.org/W3109585842","https://openalex.org/W3112108866","https://openalex.org/W4200408424","https://openalex.org/W4206169547","https://openalex.org/W4206760982","https://openalex.org/W4238767840","https://openalex.org/W4311640782","https://openalex.org/W4385318467","https://openalex.org/W4386066287","https://openalex.org/W4386076166","https://openalex.org/W4390190811","https://openalex.org/W4390874575","https://openalex.org/W4401989800","https://openalex.org/W4402727359","https://openalex.org/W4402754209","https://openalex.org/W4402816534","https://openalex.org/W4402890475","https://openalex.org/W4403842181","https://openalex.org/W6631190155","https://openalex.org/W6676449312","https://openalex.org/W6748202546","https://openalex.org/W6791353385","https://openalex.org/W6799855008","https://openalex.org/W6800751262","https://openalex.org/W6802986595","https://openalex.org/W6850625674","https://openalex.org/W6861232000","https://openalex.org/W6862027639","https://openalex.org/W6862529023"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W2123263858","https://openalex.org/W2736638679","https://openalex.org/W4313046826","https://openalex.org/W1968716783"],"abstract_inverted_index":{"Humans":[0,16],"have":[1,114],"the":[2,23,40,62,66,73,77,106,121,144,147,151,161,169,174,179,196],"remarkable":[3],"ability":[4],"to":[5,11,28,37,80,101,135,146,165,188,193],"use":[6],"held":[7,180],"objects":[8,45,145],"as":[9],"tools":[10],"interact":[12],"with":[13,31,140,191],"their":[14],"environment.":[15],"internally":[17],"estimate":[18,39],"how":[19],"hand":[20],"movements":[21],"affect":[22],"object's":[24],"movement.":[25],"We":[26,34,199],"wish":[27],"endow":[29],"robots":[30],"this":[32],"capability.":[33],"contribute":[35],"methodology":[36],"jointly":[38],"geometry":[41,64],"and":[42,118,127],"pose":[43],"of":[44,76,105,143,150,176,211],"grasped":[46,197],"by":[47,54],"a":[48,130,141,205,208],"robot,":[49],"from":[50,160],"RGB":[51],"images":[52],"captured":[53],"an":[55],"external":[56,78],"camera.":[57],"Notably,":[58],"our":[59,202],"method":[60],"transforms":[61],"estimated":[63],"into":[65],"robot's":[67],"coordinate":[68,148],"frame,":[69],"while":[70],"not":[71,113],"requiring":[72],"extrinsic":[74],"parameters":[75],"camera":[79],"be":[81,158,189],"calibrated.":[82],"Our":[83],"approach":[84,203],"leverages":[85],"<italic":[86,131],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[87,132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3D":[88],"foundation":[89],"models</i>,":[90],"large":[91],"models":[92],"pre-trained":[93],"on":[94,168,178,195,204],"huge":[95],"datasets":[96],"for":[97],"3D":[98],"vision":[99],"tasks,":[100],"produce":[102],"initial":[103,110],"estimates":[104],"in-hand":[107],"object.":[108,170],"These":[109,171],"estimations":[111],"do":[112],"physically":[115],"correct":[116],"scales":[117],"are":[119],"in":[120],"camera's":[122],"frame.":[123],"Then,":[124],"we":[125],"formulate,":[126],"efficiently":[128],"solve,":[129],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">coordinate-alignment":[133],"problem</i>":[134],"recover":[136],"accurate":[137],"scales,":[138],"along":[139],"transformation":[142],"frame":[149],"robot.":[152],"Forward":[153],"kinematics":[154],"mappings":[155,172],"can":[156],"subsequently":[157],"defined":[159],"manipulator's":[162],"joint":[163],"angles":[164],"specified":[166],"points":[167,177],"enable":[173],"estimation":[175],"object":[181],"at":[182],"arbitrary":[183],"configurations,":[184],"enabling":[185],"robot":[186],"motion":[187],"designed":[190],"respect":[192],"coordinates":[194],"objects.":[198,213],"empirically":[200],"evaluate":[201],"manipulator":[206],"holding":[207],"diverse":[209],"set":[210],"real-world":[212]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
