{"id":"https://openalex.org/W7124865827","doi":"https://doi.org/10.1109/tcsvt.2026.3655768","title":"DRPose: A Diffusion-Based Pose Refinement Framework for 3D Human Pose Estimation","display_name":"DRPose: A Diffusion-Based Pose Refinement Framework for 3D Human Pose Estimation","publication_year":2026,"publication_date":"2026-01-19","ids":{"openalex":"https://openalex.org/W7124865827","doi":"https://doi.org/10.1109/tcsvt.2026.3655768"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3655768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3655768","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Transactions on Circuits and Systems for Video Technology","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/A5123400393","display_name":"Yong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Wang","raw_affiliation_strings":["School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-7847-3807","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121373387","display_name":"Xuguang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuguang Liu","raw_affiliation_strings":["School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0007-1307-2707","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075064847","display_name":"Xupeng Wang","orcid":"https://orcid.org/0000-0001-7397-5579"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqing Wang","raw_affiliation_strings":["School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028793404","display_name":"Doudou Wu","orcid":"https://orcid.org/0000-0002-5189-8565"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Doudou Wu","raw_affiliation_strings":["School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123443965","display_name":"Wenming Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenming Yang","raw_affiliation_strings":["Shenzhen International Graduate School/Department of Electronic Engineering, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2506-1286","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School/Department of Electronic Engineering, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101145584","display_name":"Hongbo Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Kang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5771-3886","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.07125203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"6572","last_page":"6585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9736999869346619,"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":0.9736999869346619,"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":0.00930000003427267,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.006300000008195639,"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":0.8126000165939331},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.6136999726295471},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.5616000294685364},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.484499990940094},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.46939998865127563},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4316999912261963},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4284999966621399},{"id":"https://openalex.org/keywords/factor-graph","display_name":"Factor graph","score":0.4253999888896942},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.4235999882221222},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.3797999918460846}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8126000165939331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210999727249146},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.6136999726295471},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.5616000294685364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5550000071525574},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.484499990940094},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4316999912261963},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4284999966621399},{"id":"https://openalex.org/C159246509","wikidata":"https://www.wikidata.org/wiki/Q5428725","display_name":"Factor graph","level":3,"score":0.4253999888896942},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.4235999882221222},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3833000063896179},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3797999918460846},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36059999465942383},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34049999713897705},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.32510000467300415},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C107551265","wikidata":"https://www.wikidata.org/wiki/Q1458245","display_name":"Displacement (psychology)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3655768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3655768","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1648272802","display_name":null,"funder_award_id":"61673301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"two-stage":[1],"3D":[2,24,59,186],"human":[3],"pose":[4,136,187],"estimation":[5,137],"using":[6],"monocular":[7],"cameras":[8],"has":[9],"gained":[10],"significant":[11],"attention.":[12],"However,":[13],"the":[14,18,27,45,48,56,64,124,173,182],"inherent":[15],"uncertainty":[16,46],"in":[17,153,196,207],"upscaling":[19,49],"process":[20,50],"from":[21],"2D":[22],"to":[23,55,133,181],"often":[25],"compromises":[26],"accuracy":[28],"of":[29,66],"deterministic":[30],"methods.":[31],"To":[32],"address":[33],"this,":[34],"we":[35],"propose":[36],"a":[37,93,110,117,204],"novel":[38],"diffusion-based":[39],"refinement":[40,72],"framework":[41,88,147],"(DRPose)":[42],"which":[43,99,122],"models":[44],"during":[47],"by":[51],"introducing":[52],"stochastic":[53],"noise":[54,75],"initially":[57],"predicted":[58],"poses.":[60,128],"This":[61,129],"approach":[62],"facilitates":[63],"generation":[65],"more":[67],"realistic":[68],"predictions":[69,80],"through":[70],"iterative":[71],"with":[73,84,109],"multiple":[74],"samples,":[76],"ultimately":[77],"producing":[78],"multi-hypothesis":[79,190],"that":[81,166],"better":[82],"align":[83],"ground":[85],"truth.":[86],"Our":[87],"incorporates":[89],"two":[90],"key":[91],"components:":[92],"Graph":[94],"Convolution":[95],"Transformer":[96],"module":[97],"(SGCT),":[98],"integrates":[100],"scaling":[101],"and":[102,116,126,142,158,175,203],"displacement":[103],"adjustments":[104],"based":[105],"on":[106,172],"conditional":[107],"information":[108],"joint":[111],"temporal-spatial":[112],"feature":[113],"separation":[114],"mechanism,":[115],"Pose":[118],"Refinement":[119],"Module":[120],"(PRM),":[121],"balances":[123],"initial":[125],"refined":[127],"design":[130],"allows":[131],"DRPose":[132],"effectively":[134],"refine":[135],"for":[138,151],"both":[139,154],"individual":[140],"frames":[141],"sequential":[143],"data.":[144],"Furthermore,":[145],"our":[146,167,189],"establishes":[148],"new":[149],"benchmarks":[150],"performance":[152,171],"<italic":[155,159],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[156,160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">frame2frame</i>":[157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">seq2frame</i>":[161],"scenarios.":[162],"Extensive":[163],"experiments":[164],"demonstrate":[165],"method":[168],"achieves":[169,192],"state-of-the-art":[170,184],"Human3.6M":[174],"MPI-INF-3DHP":[176],"datasets.":[177],"Notably,":[178],"when":[179],"applied":[180],"current":[183],"single-frame":[185],"extractor,":[188],"optimization":[191],"an":[193],"18.8%":[194],"reduction":[195,206],"Mean":[197],"Per":[198],"Joint":[199],"Position":[200],"Error":[201],"(MPJPE)":[202],"16.9%":[205],"Procrustes":[208],"MPJPE":[209],"(P-MPJPE).":[210],"Code":[211],"is":[212],"available":[213],"at":[214],"https://github.com/KHB1698/DRPose.":[215]},"counts_by_year":[],"updated_date":"2026-05-08T13:12:06.581006","created_date":"2026-01-21T00:00:00"}