{"id":"https://openalex.org/W4417490305","doi":"https://doi.org/10.1109/iccv51701.2025.01440","title":"FreeCus: Free Lunch Subject-Driven Customization in Diffusion Transformers","display_name":"FreeCus: Free Lunch Subject-Driven Customization in Diffusion Transformers","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417490305","doi":"https://doi.org/10.1109/iccv51701.2025.01440"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01440","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.15249","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045410770","display_name":"Yanbing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137180","display_name":"Institute of High Energy Physics","ror":"https://ror.org/03v8tnc06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137180"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbing Zhang","raw_affiliation_strings":["ECUST,Key Laboratory of Smart Manufacturing in Energy Chemical Process,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECUST,Key Laboratory of Smart Manufacturing in Energy Chemical Process,China","institution_ids":["https://openalex.org/I4210137180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621319","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0002-3759-2041"},"institutions":[{"id":"https://openalex.org/I4210137180","display_name":"Institute of High Energy Physics","ror":"https://ror.org/03v8tnc06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137180"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["ECUST,Key Laboratory of Smart Manufacturing in Energy Chemical Process,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECUST,Key Laboratory of Smart Manufacturing in Energy Chemical Process,China","institution_ids":["https://openalex.org/I4210137180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022862584","display_name":"Qin Zhou","orcid":"https://orcid.org/0000-0001-5334-7188"},"institutions":[{"id":"https://openalex.org/I4210137180","display_name":"Institute of High Energy Physics","ror":"https://ror.org/03v8tnc06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137180"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Zhou","raw_affiliation_strings":["ECUST,Key Laboratory of Smart Manufacturing in Energy Chemical Process,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECUST,Key Laboratory of Smart Manufacturing in Energy Chemical Process,China","institution_ids":["https://openalex.org/I4210137180"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058786230","display_name":"Mengping Yang","orcid":"https://orcid.org/0000-0003-1503-9621"},"institutions":[{"id":"https://openalex.org/I4210149979","display_name":"Shanghai Academy of Environmental Sciences","ror":"https://ror.org/05stnhf77","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210149979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengping Yang","raw_affiliation_strings":["Shanghai Academy of Al for Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Academy of Al for Science,China","institution_ids":["https://openalex.org/I4210149979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15521","last_page":"15531"},"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":0.866100013256073,"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":0.866100013256073,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.007000000216066837,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.006300000008195639,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5378000140190125},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5101000070571899},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.484499990940094},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.448199987411499},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.42829999327659607},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3138999938964844},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.2890999913215637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7085000276565552},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5378000140190125},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.484499990940094},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.328000009059906},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv51701.2025.01440","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.15249","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15249","pdf_url":"https://arxiv.org/pdf/2507.15249","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.15249","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15249","pdf_url":"https://arxiv.org/pdf/2507.15249","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://openalex.org/G1631478713","display_name":null,"funder_award_id":"2022YFB3203500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"light":[1],"of":[2,82,137],"recent":[3],"breakthroughs":[4],"in":[5],"text-to-image":[6],"(T2I)":[7],"generation,":[8],"particularly":[9],"with":[10,203],"diffusion":[11,84],"transformers":[12,85],"(DiT),":[13],"subject-driven":[14,92],"technologies":[15],"are":[16],"increasingly":[17],"being":[18],"employed":[19],"for":[20,53,90,178],"high-fidelity":[21],"customized":[22],"production":[23],"that":[24,105,121,146,170,193],"preserves":[25],"subject":[26,54,180],"identity":[27],"from":[28],"reference":[29],"inputs,":[30],"enabling":[31],"thrilling":[32],"design":[33],"workflows":[34],"and":[35,207],"engaging":[36],"entertainment.":[37],"Existing":[38],"alternatives":[39],"typically":[40],"require":[41,194],"either":[42],"per-subject":[43],"optimization":[44],"via":[45],"trainable":[46],"text":[47],"embeddings":[48],"or":[49,187],"training":[50,63],"specialized":[51],"encoders":[52],"feature":[55,150],"extraction":[56],"on":[57,62],"large-scale":[58],"datasets.":[59],"Such":[60],"dependencies":[61],"procedures":[64],"fundamentally":[65],"constrain":[66],"their":[67],"practical":[68],"applications.":[69],"More":[70],"importantly,":[71],"current":[72],"methodologies":[73],"fail":[74],"to":[75,162,191],"fully":[76],"leverage":[77],"the":[78,87,123],"inherent":[79],"zero-shot":[80,176],"potential":[81],"modern":[83],"(e.g.,":[86],"Flux":[88],"series)":[89],"authentic":[91],"synthesis.":[93],"To":[94],"bridge":[95],"this":[96],"gap,":[97],"we":[98,141],"propose":[99,142],"FreeCus,":[100],"a":[101,116,134],"genuinely":[102],"training-free":[103],"framework":[104,199],"activates":[106],"DiT's":[107,138,175],"capabilities":[108],"through":[109],"three":[110],"key":[111],"innovations:":[112],"1)":[113],"We":[114,153],"introduce":[115],"pivotal":[117],"attention":[118],"sharing":[119],"mechanism":[120],"captures":[122],"subject's":[124],"layout":[125],"integrity":[126],"while":[127],"preserving":[128],"crucial":[129],"editing":[130],"flexibility.":[131],"2)":[132],"Through":[133],"straightforward":[135],"analysis":[136],"dynamic":[139],"shifting,":[140],"an":[143],"upgraded":[144],"variant":[145],"significantly":[147],"improves":[148],"fine-grained":[149],"extraction.":[151],"3)":[152],"further":[154],"integrate":[155],"advanced":[156],"Multimodal":[157],"Large":[158],"Language":[159],"Models":[160],"(MLLMs)":[161],"enrich":[163],"cross-modal":[164],"semantic":[165],"representations.":[166],"Extensive":[167],"experiments":[168],"reflect":[169],"our":[171,198],"method":[172],"successfully":[173],"unlocks":[174],"ability":[177],"consistent":[179],"synthesis":[181],"across":[182],"diverse":[183],"contexts,":[184],"achieving":[185],"state-of-the-art":[186],"comparable":[188],"results":[189],"compared":[190],"approaches":[192],"additional":[195],"training.":[196],"Notably,":[197],"demonstrates":[200],"seamless":[201],"compatibility":[202],"existing":[204],"inpainting":[205],"pipelines":[206],"control":[208],"modules,":[209],"facilitating":[210],"more":[211],"compelling":[212],"experiences.":[213],"Our":[214],"code":[215],"is":[216],"available":[217],"at:":[218],"https://github.com/Monalissaa/FreeCus.":[219]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}