{"id":"https://openalex.org/W7117108270","doi":"https://doi.org/10.1109/tpami.2025.3647855","title":"Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimation","display_name":"Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimation","publication_year":2025,"publication_date":"2025-12-24","ids":{"openalex":"https://openalex.org/W7117108270","doi":"https://doi.org/10.1109/tpami.2025.3647855","pmid":"https://pubmed.ncbi.nlm.nih.gov/41442298"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3647855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3647855","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5055922003","display_name":"Jingtao Sun","orcid":"https://orcid.org/0000-0001-5087-1304"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jingtao Sun","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-5087-1304","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121240487","display_name":"Yaonan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yaonan Wang","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-0519-6458","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022848316","display_name":"Mingtao Feng","orcid":"https://orcid.org/0000-0003-0384-3743"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mingtao Feng","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-0384-3743","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chao Ding","orcid":"https://orcid.org/0000-0001-8111-7056"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chao Ding","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-8111-7056","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mike Zheng Shou","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Show Lab, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7681-2166","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Show Lab, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089986388","display_name":"Ajmal Mian","orcid":"https://orcid.org/0000-0002-5206-3842"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ajmal Mian","raw_affiliation_strings":["Computer Science and Software Engineering, The University of Western Australia (UWA), Perth, Western Australia, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5206-3842","affiliations":[{"raw_affiliation_string":"Computer Science and Software Engineering, The University of Western Australia (UWA), Perth, Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":0.52907703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"5","first_page":"5113","last_page":"5130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.6040999889373779,"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":0.6040999889373779,"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":0.3248000144958496,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.012900000438094139,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.8169999718666077},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6370999813079834},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.5152000188827515},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49639999866485596},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46299999952316284},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.445499986410141},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4426000118255615},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4163999855518341},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.40619999170303345}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8169999718666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8059999942779541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677000164985657},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6370999813079834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5454999804496765},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.5152000188827515},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.445499986410141},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4163999855518341},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.40619999170303345},{"id":"https://openalex.org/C129641003","wikidata":"https://www.wikidata.org/wiki/Q267189","display_name":"Active shape model","level":3,"score":0.3955000042915344},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33709999918937683},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C118317068","wikidata":"https://www.wikidata.org/wiki/Q2100760","display_name":"Point distribution model","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3647855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3647855","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41442298","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41442298","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":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3968842904","display_name":null,"funder_award_id":"NRF-NRFF13-2021-0008","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fully-supervised":[0],"category-level":[1,24,191,200],"pose":[2,25,58,85,97],"estimation":[3,26],"aims":[4],"to":[5,31,55,93,143,151],"determine":[6],"the":[7,33,36,89,95,153,161,169],"6-DoF":[8],"poses":[9],"of":[10,35,163],"unseen":[11],"instances":[12],"from":[13],"known":[14],"categories,":[15],"requiring":[16],"expensive":[17],"manual":[18],"labeling":[19],"costs.":[20],"Recently,":[21],"various":[22],"self-supervised":[23,77,190],"methods":[27,41],"have":[28],"been":[29],"proposed":[30,149],"reduce":[32],"requirement":[34],"annotated":[37],"datasets.":[38],"However,":[39],"most":[40],"rely":[42],"on":[43,175],"synthetic":[44],"data":[45],"or":[46,64],"3D":[47,100,109,126],"CAD":[48],"model,":[49],"and":[50,71,83,99,124,158,179,193,199],"they":[51],"are":[52],"typically":[53],"limited":[54],"addressing":[56,160],"single-object":[57],"problems":[59],"without":[60],"considering":[61],"multi-objective":[62],"tasks":[63],"shape":[65,81,90,102,133,156,165],"reconstruction.":[66],"To":[67],"overcome":[68],"these":[69],"challenges":[70],"limitations,":[72],"we":[73,104,136],"introduce":[74,137],"a":[75,106,115,125,138,180],"diffusion-driven":[76],"network":[78,150],"for":[79,121,131],"multi-object":[80],"reconstruction":[82],"categorical":[84],"estimation,":[86],"only":[87],"leveraging":[88],"priors.":[91],"Specifically,":[92],"capture":[94,152],"SE(3)-equivariant":[96],"features":[98],"scale-invariant":[101,127],"information,":[103],"present":[105],"Prior-Aware":[107],"Pyramid":[108],"Point":[110],"Transformer.":[111],"This":[112],"module":[113],"adopts":[114],"point":[116],"convolutional":[117],"layer":[118,130],"with":[119],"radial-kernels":[120],"pose-aware":[122],"learning":[123],"graph":[128],"convolution":[129],"object-level":[132],"representation.":[134],"Furthermore,":[135],"Pretrain-to-Refine":[139],"Self-Supervised":[140],"Training":[141],"Paradigm":[142],"train":[144],"our":[145,185],"network.":[146],"It":[147],"enables":[148],"associations":[154],"between":[155],"priors":[157],"observations,":[159],"challenge":[162],"intra-class":[164],"variations":[166],"by":[167],"utilising":[168],"diffusion":[170],"mechanism.":[171],"Extensive":[172],"experiments":[173],"conducted":[174],"four":[176],"public":[177],"datasets":[178],"self-built":[181],"dataset":[182],"demonstrate":[183],"that":[184],"method":[186],"significantly":[187],"outperforms":[188],"state-of-the-art":[189],"baselines":[192],"even":[194],"surpasses":[195],"some":[196],"fully-supervised":[197],"instance-level":[198],"methods.":[201],"The":[202],"project":[203],"page":[204],"is":[205],"released":[206],"at":[207],"Self-SRPE.":[208]},"counts_by_year":[],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2025-12-24T00:00:00"}