{"id":"https://openalex.org/W4417295369","doi":"https://doi.org/10.1109/wacv61042.2026.00652","title":"Point2Pose: A Generative Framework for 3D Human Pose Estimation with Multi-View Point Cloud Dataset","display_name":"Point2Pose: A Generative Framework for 3D Human Pose Estimation with Multi-View Point Cloud Dataset","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417295369","doi":"https://doi.org/10.1109/wacv61042.2026.00652"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00652","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/2512.10321","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088349384","display_name":"Hyunsoo Lee","orcid":"https://orcid.org/0000-0001-5512-2986"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunsoo Lee","raw_affiliation_strings":["Seoul National University,ECE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,ECE","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Daeum Jeon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Daeum Jeon","raw_affiliation_strings":["KAIST,CS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,CS","institution_ids":["https://openalex.org/I4210099236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087630155","display_name":"Hyun-Ung Oh","orcid":"https://orcid.org/0000-0003-2161-7272"},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hyeokjae Oh","raw_affiliation_strings":["KAIST,CS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,CS","institution_ids":["https://openalex.org/I4210099236"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.03113984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6744","last_page":"6753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.8968999981880188,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.8968999981880188,"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/T12290","display_name":"Human Motion and Animation","score":0.03880000114440918,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.011500000022351742,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/point-cloud","display_name":"Point cloud","score":0.8136000037193298},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.7842000126838684},{"id":"https://openalex.org/keywords/inertial-measurement-unit","display_name":"Inertial measurement unit","score":0.5669000148773193},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.541100025177002},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.5396999716758728},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5299000144004822},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5205000042915344},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5005000233650208},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.4699999988079071}],"concepts":[{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.8136000037193298},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7842000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7540000081062317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384999990463257},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6001999974250793},{"id":"https://openalex.org/C79061980","wikidata":"https://www.wikidata.org/wiki/Q941680","display_name":"Inertial measurement unit","level":2,"score":0.5669000148773193},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.5396999716758728},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5005000233650208},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.4699999988079071},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3824000060558319},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.33889999985694885},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00652","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:2512.10321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10321","pdf_url":"https://arxiv.org/pdf/2512.10321","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2512.10321","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.10321","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.10321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10321","pdf_url":"https://arxiv.org/pdf/2512.10321","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,45,66,72,89],"novel":[3],"generative":[4,84],"approach":[5],"for":[6,33],"3D":[7,11],"human":[8,12,26,53,103],"pose":[9,13,61,73],"estimation.":[10],"estimation":[14],"poses":[15,54],"several":[16],"key":[17],"challenges":[18],"due":[19],"to":[20,76],"the":[21,25,31,50,116,120],"complex":[22],"geometry":[23],"of":[24,52,101],"body,":[27],"self-occluding":[28],"joints,":[29],"and":[30,60,71,109],"requirement":[32],"large-scale":[34,90],"real-world":[35],"motion":[36],"datasets.":[37,129],"To":[38],"address":[39],"these":[40],"challenges,":[41],"we":[42,64,87],"introduce":[43],"Point2Pose,":[44],"framework":[46],"that":[47,115],"effectively":[48],"models":[49],"distribution":[51],"conditioned":[55],"on":[56],"sequential":[57],"point":[58,68,107],"cloud":[59,69],"history.":[62],"Specifically,":[63],"employ":[65],"spatio-temporal":[67],"encoder":[70,75],"feature":[74],"extract":[77],"joint-wise":[78],"features,":[79],"followed":[80],"by":[81],"an":[82],"attention-based":[83],"regressor.":[85],"Additionally,":[86],"present":[88],"indoor":[91],"dataset":[92],"MVPose3D,":[93],"which":[94],"contains":[95],"multiple":[96],"modalities,":[97],"including":[98],"IMU":[99],"data":[100],"non-trivial":[102],"motions,":[104],"dense":[105],"multi-view":[106],"clouds,":[108],"RGB":[110],"images.":[111],"Experimental":[112],"results":[113],"show":[114],"proposed":[117],"method":[118],"outperforms":[119],"baseline":[121],"models,":[122],"demonstrating":[123],"its":[124],"superior":[125],"performance":[126],"across":[127],"various":[128]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-12-13T00:00:00"}