{"id":"https://openalex.org/W4414404702","doi":"https://doi.org/10.1109/tmm.2025.3613113","title":"StableIdentity: Inserting Anybody Into Anywhere at First Sight","display_name":"StableIdentity: Inserting Anybody Into Anywhere at First Sight","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414404702","doi":"https://doi.org/10.1109/tmm.2025.3613113"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3613113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3613113","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5111121368","display_name":"Qinghe Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghe Wang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-6908-5485","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu Jia","orcid":"https://orcid.org/0000-0003-3168-3505"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Jia","raw_affiliation_strings":["School of Artificial Intelligence, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-3168-3505","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104236776","display_name":"Xiaomin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomin Li","raw_affiliation_strings":["School of Artificial Intelligence, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-7202-6865","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093826608","display_name":"Taiqing Li","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taiqing Li","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0008-5409-6753","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093826609","display_name":"Liqian Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqian Ma","raw_affiliation_strings":["ZMO.AI Inc., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0814-9876","affiliations":[{"raw_affiliation_string":"ZMO.AI Inc., Shenzhen, China","institution_ids":["https://openalex.org/I4210098582"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093826610","display_name":"Yunzhi Zhuge","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunzhi Zhuge","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-4288-4516","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huchuan Lu","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-6668-9758","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6574,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.93129202,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"9342","last_page":"9353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11445","display_name":"Origins and Evolution of Life","score":0.01600000075995922,"subfield":{"id":"https://openalex.org/subfields/3103","display_name":"Astronomy and Astrophysics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11445","display_name":"Origins and Evolution of Life","score":0.01600000075995922,"subfield":{"id":"https://openalex.org/subfields/3103","display_name":"Astronomy and Astrophysics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.009700000286102295,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.006200000178068876,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.7372000217437744},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5461000204086304},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47530001401901245},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.46720001101493835},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41780000925064087},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4147999882698059},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.3668999969959259},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.3361000120639801},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.33309999108314514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8529999852180481},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.7372000217437744},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5209000110626221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.512499988079071},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47530001401901245},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.46720001101493835},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41780000925064087},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3361000120639801},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C1517167","wikidata":"https://www.wikidata.org/wiki/Q1134322","display_name":"Sight","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3613113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3613113","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2558812161","display_name":null,"funder_award_id":"U23B2010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4175600677","display_name":null,"funder_award_id":"62472065","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4585823974","display_name":null,"funder_award_id":"62441231","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2294798173","https://openalex.org/W2559085405","https://openalex.org/W2797558164","https://openalex.org/W2886934227","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2969985801","https://openalex.org/W3180355996","https://openalex.org/W4285981780","https://openalex.org/W4312419008","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W4376481222","https://openalex.org/W4377715513","https://openalex.org/W4378648070","https://openalex.org/W4385152034","https://openalex.org/W4385318467","https://openalex.org/W4385953069","https://openalex.org/W4386071831","https://openalex.org/W4386072096","https://openalex.org/W4386702700","https://openalex.org/W4387449209","https://openalex.org/W4389539271","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4390874393","https://openalex.org/W4392902491","https://openalex.org/W4393148714","https://openalex.org/W4393149651","https://openalex.org/W4393253100","https://openalex.org/W4396817358","https://openalex.org/W4399206493","https://openalex.org/W4402703076","https://openalex.org/W4402727912","https://openalex.org/W4402753775","https://openalex.org/W4402774219","https://openalex.org/W4402775813","https://openalex.org/W4402782221","https://openalex.org/W4406610835","https://openalex.org/W4412352576"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"large":[3],"pretrained":[4],"text-to-image":[5],"generation":[6,195,215],"models":[7],"have":[8],"shown":[9],"unprecedented":[10],"capabilities":[11],"for":[12,39,63],"high-quality":[13],"human-centric":[14],"generation,":[15],"however,":[16],"customizing":[17],"face":[18,57,72,87,140],"identity":[19,30,76,108,115,160,187],"is":[20,101,204,219],"still":[21],"an":[22,205],"intractable":[23],"problem.":[24],"Existing":[25],"methods":[26],"cannot":[27],"ensure":[28],"stable":[29],"preservation":[31],"and":[32,83,110,141,212],"flexible":[33],"editability,":[34],"even":[35],"with":[36,54,74,96,120,165],"several":[37],"images":[38],"each":[40],"subject":[41],"during":[42],"training.":[43],"In":[44,123,156],"this":[45],"work,":[46],"we":[47,69,125,179],"propose":[48],"StableIdentity,":[49],"which":[50,100],"allows":[51],"identity-consistent":[52],"recontextualization":[53],"just":[55],"one":[56],"image":[58,192],"from":[59,103,189],"a":[60,71,94,127,190],"person":[61],"seen":[62],"the":[64,75,80,86,91,97,113,134,138,143,158,166,174,181,186,201],"first":[65,182],"time.":[66],"More":[67],"specifically,":[68],"employ":[70],"encoder":[73],"prior":[77,109],"to":[78,89,132,173,183,208],"encode":[79],"input":[81,139],"face,":[82],"then":[84],"calibrate":[85],"representation":[88],"align":[90],"distribution":[92],"of":[93,137,145,176],"space":[95],"editability":[98,111],"prior,":[99,112],"constructed":[102],"celeb":[104],"names.":[105],"By":[106],"incorporating":[107],"learned":[114,159,188],"can":[116,161],"be":[117,162],"injected":[118],"anywhere":[119],"various":[121],"contexts.":[122],"addition,":[124,157],"design":[126],"masked":[128],"two-phase":[129],"diffusion":[130],"loss":[131],"boost":[133],"pixel-level":[135],"perception":[136],"maintain":[142],"diversity":[144],"generation.":[146],"Extensive":[147],"experiments":[148],"demonstrate":[149],"our":[150,177],"method":[151],"outperforms":[152],"previous":[153],"customization":[154],"methods.":[155],"flexibly":[163],"combined":[164],"off-theshelf":[167],"modules":[168],"such":[169],"as":[170],"ControlNet.":[171],"Notably,":[172],"best":[175],"knowledge,":[178],"are":[180],"directly":[184],"inject":[185],"single":[191],"into":[193],"video/3D":[194],"without":[196],"finetuning.":[197],"We":[198],"believe":[199],"that":[200],"proposed":[202],"StableIdentity":[203],"important":[206],"step":[207],"unify":[209],"image,":[210],"video,":[211],"3D":[213],"customized":[214],"models.":[216],"The":[217],"code":[218],"available:":[220],"https://github.com/qinghew/StableIdentity.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-19T00:32:22.182498","created_date":"2025-10-10T00:00:00"}
