{"id":"https://openalex.org/W4416749185","doi":"https://doi.org/10.1109/tcsvt.2025.3637822","title":"IP-Controller: Decomposition and Optimization of Cross-Attention Maps for Accurate Subject-Driven Text-to-Image Diffusion Generation","display_name":"IP-Controller: Decomposition and Optimization of Cross-Attention Maps for Accurate Subject-Driven Text-to-Image Diffusion Generation","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W4416749185","doi":"https://doi.org/10.1109/tcsvt.2025.3637822"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3637822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3637822","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/A5063462595","display_name":"Junsheng Luan","orcid":"https://orcid.org/0009-0009-2902-8086"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junsheng Luan","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-2902-8086","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101603720","display_name":"Guangyuan Li","orcid":"https://orcid.org/0000-0002-2938-527X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyuan Li","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2938-527X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061370730","display_name":"Zhanjie Zhang","orcid":"https://orcid.org/0000-0002-8966-1328"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanjie Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8966-1328","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064842786","display_name":"Lei Zhao","orcid":"https://orcid.org/0000-0003-4791-454X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4791-454X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100681865","display_name":"Wei Xing","orcid":"https://orcid.org/0000-0002-7994-6725"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xing","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7994-6725","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I168879160"],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77708131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"36","issue":"4","first_page":"5274","last_page":"5287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9620000123977661,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9620000123977661,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.0071000000461936,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.003000000026077032,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7515000104904175},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6798999905586243},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5785999894142151},{"id":"https://openalex.org/keywords/mistake","display_name":"Mistake","score":0.5667999982833862},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4986000061035156},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48179998993873596},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.37310001254081726}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7515000104904175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7156999707221985},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6798999905586243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6179999709129333},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5785999894142151},{"id":"https://openalex.org/C2777179996","wikidata":"https://www.wikidata.org/wiki/Q911222","display_name":"Mistake","level":2,"score":0.5667999982833862},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3418000042438507},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.26499998569488525}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3637822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3637822","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Although":[0],"large":[1],"pretrained":[2],"stable":[3],"diffusion":[4,238],"(SD)":[5],"models":[6],"can":[7],"generate":[8,15,160,200],"high-quality":[9,280],"images":[10,16,281],"from":[11,74],"prompts,":[12,216],"they":[13,72],"cannot":[14],"that":[17,98,236,248],"are":[18],"consistent":[19],"with":[20,105,226],"the":[21,45,53,99,106,161,208,211,220,227,237,252,263,267,283],"fine-grained":[22],"characteristics":[23],"of":[24,55,86,124,140,210,255,266],"a":[25,49,83,94,165,185],"specific":[26,244],"identity":[27],"<italic":[28,87,125,141,152,178,194,256,272],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[29,32,88,91,126,129,142,145,153,156,179,182,195,257,260,273,276],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">V</i>":[30,89,127,143,154,180,196,258,274],"<sup":[31,90,128,144,155,181,259,275],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u2217</sup>":[33,146,261,277],"(e.g.,":[34],"an":[35,173],"anime":[36],"character).":[37],"Subject-driven":[38],"generation":[39],"focuses":[40],"on":[41,207],"exploring":[42],"and":[43,57,76,93,136,147,169,184,203,214,222,230,262,278],"leveraging":[44],"prior":[46],"knowledge":[47],"within":[48],"model":[50],"to":[51,67],"achieve":[52],"goals":[54],"ID":[56,75,80,174,202,213,221,229],"context":[58,77,95,186,204,215,223,231,265],"preservation.":[59],"There":[60],"have":[61],"been":[62],"efforts,":[63],"such":[64],"as":[65],"DreamBooth,":[66],"conduct":[68],"subject-driven":[69],"generation;":[70],"however,":[71],"suffer":[73],"mistakes.":[78],"An":[79],"mistake":[81,96],"means":[82,97],"feature":[84,122],"loss":[85],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u2217</sup>,":[92,130],"generated":[100],"image":[101],"does":[102],"not":[103],"align":[104],"given":[107,284],"prompt.":[108,285],"To":[109],"rectify":[110],"these":[111],"problems,":[112],"in":[113],"this":[114],"paper,":[115],"we":[116,159,199],"propose":[117,132],"masked":[118],"fine-tuning":[119],"for":[120,134,243,282],"efficient":[121],"learning":[123],"then":[131],"IP-Controller":[133,249],"decomposing":[135],"optimizing":[137],"cross-attention":[138,162,175,187,205,224,232],"maps":[139,206,225],"prompt":[148,168,190,268],"words":[149,191,269],"other":[150,192,270],"than":[151,193,271],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u2217</sup>.":[157],"Specifically,":[158],"map":[163,176,188],"using":[164],"vanilla":[166],"input":[167,212],"decompose":[170],"it":[171],"into":[172],"(matching":[177,189],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u2217</sup>)":[183],"\u2217).":[197],"Next,":[198],"fitter":[201,228,241],"basis":[209],"respectively.":[217],"We":[218],"optimize":[219],"maps,":[233],"respectively,":[234],"so":[235],"process":[239],"pays":[240],"attention":[242],"contents.":[245],"Experiments":[246],"show":[247],"correctly":[250],"integrates":[251],"core":[253],"features":[254],"semantic":[264],"generates":[279]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2025-11-28T00:00:00"}
