{"id":"https://openalex.org/W4405032013","doi":"https://doi.org/10.1109/iccv51701.2025.01386","title":"OminiControl: Minimal and Universal Control for Diffusion Transformer","display_name":"OminiControl: Minimal and Universal Control for Diffusion Transformer","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405032013","doi":"https://doi.org/10.1109/iccv51701.2025.01386"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01386","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.15098","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101336174","display_name":"Zhenxiong Tan","orcid":null},"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":"Zhenxiong Tan","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101559354","display_name":"Songhua Liu","orcid":"https://orcid.org/0000-0003-1033-5122"},"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":"Songhua Liu","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080003280","display_name":"Xingyi Yang","orcid":"https://orcid.org/0000-0002-1603-9829"},"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":"Xingyi Yang","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063417015","display_name":"Qiao Xue","orcid":"https://orcid.org/0000-0001-5523-3918"},"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":"Qiaochu Xue","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015574447","display_name":"Xinchao Wang","orcid":"https://orcid.org/0000-0003-0057-1404"},"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":"Xinchao Wang","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9811,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70995061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"14940","last_page":"14950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10323","display_name":"Analog and Mixed-Signal Circuit Design","score":0.8220000267028809,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10323","display_name":"Analog and Mixed-Signal Circuit Design","score":0.8220000267028809,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/transformer","display_name":"Transformer","score":0.471064031124115},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.41157087683677673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.383749783039093},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3370189964771271},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.3191630244255066},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.26083290576934814},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.19801083207130432},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16649344563484192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13766303658485413},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12272101640701294},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.11785227060317993}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.471064031124115},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.41157087683677673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.383749783039093},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3370189964771271},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.3191630244255066},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26083290576934814},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.19801083207130432},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16649344563484192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13766303658485413},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12272101640701294},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.11785227060317993}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01386","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:2411.15098","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.15098","pdf_url":"https://arxiv.org/pdf/2411.15098","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.15098","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.15098","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.15098","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.15098","pdf_url":"https://arxiv.org/pdf/2411.15098","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2864363823"],"abstract_inverted_index":{"We":[0],"present":[1],"OminiControl,":[2],"a":[3,47,67,85,132],"novel":[4],"approach":[5,106],"that":[6,51,72,90,103,147],"rethinks":[7],"how":[8],"image":[9,19,77,137,149,164],"conditions":[10],"are":[11],"integrated":[12],"into":[13],"Diffusion":[14],"Transformer":[15],"(DiT)":[16],"architectures.":[17],"Current":[18],"conditioning":[20,119],"methods":[21,116],"either":[22],"introduce":[23,130],"substantial":[24],"parameter":[25],"overhead":[26],"or":[27],"handle":[28],"only":[29,108],"specific":[30],"control":[31,97,150],"tasks":[32],"effectively,":[33],"limiting":[34],"their":[35],"practical":[36],"versatility.":[37],"OminiControl":[38],"addresses":[39],"these":[40],"limitations":[41,124],"through":[42],"three":[43],"key":[44],"innovations:":[45],"(1)":[46],"minimal":[48],"architectural":[49,155],"design":[50],"leverages":[52],"the":[53,112],"DiT's":[54],"own":[55],"VAE":[56],"encoder":[57],"and":[58,83,95,162],"transformer":[59],"blocks,":[60],"requiring":[61],"just":[62],"0.1%":[63],"additional":[64],"parameters;":[65],"(2)":[66],"unified":[68],"sequence":[69],"processing":[70],"strategy":[71],"combines":[73],"condition":[74],"tokens":[75,78],"with":[76],"for":[79,160],"flexible":[80],"token":[81],"interactions;":[82],"(3)":[84],"dynamic":[86],"position":[87],"encoding":[88],"mechanism":[89],"adapts":[91],"to":[92],"both":[93],"spatially-aligned":[94],"non-aligned":[96],"tasks.":[98,120],"Our":[99],"extensive":[100],"experiments":[101],"show":[102],"this":[104],"streamlined":[105],"not":[107],"matches":[109],"but":[110],"surpasses":[111],"performance":[113],"of":[114,135],"specialized":[115],"across":[117],"multiple":[118],"To":[121],"overcome":[122],"data":[123],"in":[125],"subject-driven":[126],"generation,":[127],"we":[128],"also":[129],"Subjects200K,":[131],"large-scale":[133],"dataset":[134],"identity-consistent":[136],"pairs":[138],"synthesized":[139],"using":[140],"DiT":[141],"models":[142],"themselves.":[143],"This":[144],"work":[145],"demonstrates":[146],"effective":[148],"can":[151],"be":[152],"achieved":[153],"without":[154],"complexity,":[156],"opening":[157],"new":[158],"possibilities":[159],"efficient":[161],"versatile":[163],"generation":[165],"systems.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
