{"id":"https://openalex.org/W4415644673","doi":"https://doi.org/10.3390/jimaging11110380","title":"Pov9D: Point Cloud-Based Open-Vocabulary 9D Object Pose Estimation","display_name":"Pov9D: Point Cloud-Based Open-Vocabulary 9D Object Pose Estimation","publication_year":2025,"publication_date":"2025-10-28","ids":{"openalex":"https://openalex.org/W4415644673","doi":"https://doi.org/10.3390/jimaging11110380","pmid":"https://pubmed.ncbi.nlm.nih.gov/41295097"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging11110380","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11110380","pdf_url":"https://www.mdpi.com/2313-433X/11/11/380/pdf?version=1761650102","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/11/11/380/pdf?version=1761650102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101716205","display_name":"Tianfu Wang","orcid":"https://orcid.org/0000-0001-6644-7233"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianfu Wang","raw_affiliation_strings":["State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences, Chuangxin Road 135, Shenyang 110016, China","University of Chinese Academy of Sciences, Yuquan Road 19, Beijing 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences, Chuangxin Road 135, Shenyang 110016, China","institution_ids":["https://openalex.org/I142078773"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Yuquan Road 19, Beijing 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086025983","display_name":"H. G. Wang","orcid":"https://orcid.org/0000-0002-2044-5184"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongguang Wang","raw_affiliation_strings":["State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences, Chuangxin Road 135, Shenyang 110016, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences, Chuangxin Road 135, Shenyang 110016, China","institution_ids":["https://openalex.org/I142078773"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086025983"],"corresponding_institution_ids":["https://openalex.org/I142078773"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37944356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"11","first_page":"380","last_page":"380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8615999817848206,"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":0.8615999817848206,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.028300000354647636,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.022199999541044235,"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/pose","display_name":"Pose","score":0.8385999798774719},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.7432000041007996},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6987000107765198},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5799999833106995},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5692999958992004},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.531000018119812},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.5151000022888184},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39160001277923584},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.38119998574256897}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8385999798774719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7918999791145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756999731063843},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.7432000041007996},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7358999848365784},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6987000107765198},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5799999833106995},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5692999958992004},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.531000018119812},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.5151000022888184},{"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/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.38119998574256897},{"id":"https://openalex.org/C129641003","wikidata":"https://www.wikidata.org/wiki/Q267189","display_name":"Active shape model","level":3,"score":0.35899999737739563},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.32190001010894775},{"id":"https://openalex.org/C112604564","wikidata":"https://www.wikidata.org/wiki/Q7489226","display_name":"Shape analysis (program analysis)","level":3,"score":0.3165000081062317},{"id":"https://openalex.org/C181095308","wikidata":"https://www.wikidata.org/wiki/Q1541599","display_name":"Geometric primitive","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C23903533","wikidata":"https://www.wikidata.org/wiki/Q17122739","display_name":"Reprojection error","level":3,"score":0.2793999910354614},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/jimaging11110380","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11110380","pdf_url":"https://www.mdpi.com/2313-433X/11/11/380/pdf?version=1761650102","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:41295097","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41295097","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":"Journal of imaging","raw_type":null},{"id":"pmh:oai:doaj.org/article:c24f6817f6654373bd48078af251b46f","is_oa":true,"landing_page_url":"https://doaj.org/article/c24f6817f6654373bd48078af251b46f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 11, Iss 11, p 380 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/jimaging11110380","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11110380","pdf_url":"https://www.mdpi.com/2313-433X/11/11/380/pdf?version=1761650102","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415644673.pdf","grobid_xml":"https://content.openalex.org/works/W4415644673.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W132147841","https://openalex.org/W2115579991","https://openalex.org/W2122122381","https://openalex.org/W2128019145","https://openalex.org/W2344474200","https://openalex.org/W2560722161","https://openalex.org/W2777195424","https://openalex.org/W2962783853","https://openalex.org/W2963188159","https://openalex.org/W2963892972","https://openalex.org/W2964249569","https://openalex.org/W3034573608","https://openalex.org/W3107992529","https://openalex.org/W3202459445","https://openalex.org/W3216621076","https://openalex.org/W4221167977","https://openalex.org/W4225435562","https://openalex.org/W4294691680","https://openalex.org/W4298014068","https://openalex.org/W4312251507","https://openalex.org/W4386065742","https://openalex.org/W4386071598","https://openalex.org/W4386075656","https://openalex.org/W4386076097","https://openalex.org/W4390873470","https://openalex.org/W4400726600","https://openalex.org/W4402727846","https://openalex.org/W4402753846","https://openalex.org/W4402754209","https://openalex.org/W4413145353","https://openalex.org/W7083000843"],"related_works":[],"abstract_inverted_index":{"framework":[0],"for":[1,54,129],"open-vocabulary":[2,62],"object":[3,98,123],"pose":[4,25,58],"estimation,":[5,59],"called":[6],"Pov9D.":[7],"Existing":[8],"approaches":[9],"are":[10,29,52],"predominantly":[11],"RGB-based":[12],"and":[13,56,71,106,126,149],"often":[14],"rely":[15],"on":[16,134],"texture":[17],"or":[18,31],"appearance":[19],"cues,":[20],"making":[21],"them":[22],"susceptible":[23],"to":[24,48,79],"ambiguities":[26],"when":[27],"objects":[28],"textureless":[30],"lack":[32],"distinctive":[33],"visual":[34],"features.":[35],"In":[36],"contrast,":[37],"Pov9D":[38,74,140],"takes":[39],"3D":[40],"point":[41,104],"clouds":[42],"as":[43],"input,":[44],"enabling":[45],"direct":[46],"access":[47],"geometric":[49,69,117],"structures":[50],"that":[51,94,139],"essential":[53],"accurate":[55],"robust":[57],"especially":[60],"in":[61],"settings.":[63],"To":[64,84],"bridge":[65],"the":[66,81,102,107,135],"gap":[67],"between":[68],"observations":[70],"semantic":[72],"understanding,":[73],"integrates":[75],"category-level":[76],"textual":[77,108],"descriptions":[78],"guide":[80],"estimation":[82],"process.":[83],"this":[85],"end,":[86],"we":[87],"introduce":[88],"a":[89,96,115],"text-conditioned":[90],"shape":[91,99,112],"prior":[92,113],"generator":[93],"predicts":[95],"normalized":[97],"from":[100],"both":[101],"observed":[103],"cloud":[105],"category":[109],"description.":[110],"This":[111],"provides":[114],"consistent":[116],"reference,":[118],"facilitating":[119],"precise":[120],"prediction":[121],"of":[122],"translation,":[124],"rotation,":[125],"size,":[127],"even":[128],"unseen":[130],"categories.":[131],"Extensive":[132],"experiments":[133],"OO3D-9D":[136],"benchmark":[137],"demonstrate":[138],"achieves":[141],"state-of-the-art":[142],"performance,":[143],"improving":[144],"Abs":[145],"IoU@50":[146],"by":[147,154],"7.2%":[148],"Rel":[150],"10\u00b0":[151],"10":[152],"cm":[153],"27.2%":[155],"over":[156],"OV9D.":[157]},"counts_by_year":[],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-29T00:00:00"}