{"id":"https://openalex.org/W4415102468","doi":"https://doi.org/10.1109/iccv51701.2025.01703","title":"Unicombine: Unified Multi-Conditional Combination with Diffusion Transformer","display_name":"Unicombine: Unified Multi-Conditional Combination with Diffusion Transformer","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415102468","doi":"https://doi.org/10.1109/iccv51701.2025.01703"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01703","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.09277","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000220618","display_name":"Haoxuan Wang","orcid":"https://orcid.org/0000-0002-8663-3073"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxuan Wang","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinlong Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Peng","raw_affiliation_strings":["Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010996897","display_name":"Qingdong He","orcid":"https://orcid.org/0000-0003-3203-0071"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingdong He","raw_affiliation_strings":["Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042938598","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0002-6997-6963"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102737538","display_name":"Ying Jin","orcid":"https://orcid.org/0000-0002-6364-8301"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Jin","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025002931","display_name":"Jiafu Wu","orcid":"https://orcid.org/0000-0002-1036-5076"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafu Wu","raw_affiliation_strings":["Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066970325","display_name":"Xiaobin Hu","orcid":"https://orcid.org/0000-0003-2919-3371"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobin Hu","raw_affiliation_strings":["Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012153627","display_name":"Yi Pan","orcid":"https://orcid.org/0000-0002-0090-1285"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjie Pan","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012172321","display_name":"Zhenye Gan","orcid":"https://orcid.org/0000-0003-1477-4958"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenye Gan","raw_affiliation_strings":["Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057267422","display_name":"Mingmin Chi","orcid":"https://orcid.org/0000-0003-2650-4146"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingmin Chi","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010159266","display_name":"Bo Peng","orcid":"https://orcid.org/0000-0002-8694-5106"},"institutions":[{"id":"https://openalex.org/I44675526","display_name":"Shanghai Ocean University","ror":"https://ror.org/04n40zv07","country_code":"CN","type":"education","lineage":["https://openalex.org/I44675526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Peng","raw_affiliation_strings":["Shanghai Ocean University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Ocean University","institution_ids":["https://openalex.org/I44675526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabiao Wang","raw_affiliation_strings":["Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":"18325","last_page":"18334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.41600000858306885,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.41600000858306885,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.3562999963760376,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10299","display_name":"Photonic and Optical Devices","score":0.3456999957561493,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/generative-grammar","display_name":"Generative grammar","score":0.6550999879837036},{"id":"https://openalex.org/keywords/universality","display_name":"Universality (dynamical systems)","score":0.5568000078201294},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46389999985694885},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.40860000252723694},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.36000001430511475},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3490999937057495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6721000075340271},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6550999879837036},{"id":"https://openalex.org/C183992945","wikidata":"https://www.wikidata.org/wiki/Q2495574","display_name":"Universality (dynamical systems)","level":2,"score":0.5568000078201294},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46389999985694885},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40549999475479126},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3490999937057495},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.26190000772476196}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01703","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:2503.09277","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.09277","pdf_url":"https://arxiv.org/pdf/2503.09277","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"},{"id":"doi:10.48550/arxiv.2503.09277","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.09277","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.09277","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.09277","pdf_url":"https://arxiv.org/pdf/2503.09277","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/G2728175297","display_name":null,"funder_award_id":"62171139","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,10,30,96,110,120,132],"rapid":[2],"development":[3],"of":[4,32,43,60,64,138],"diffusion":[5],"models":[6],"in":[7],"image":[8],"generation,":[9],"demand":[11],"for":[12,114],"more":[13],"powerful":[14,136],"and":[15,75,87,98,122,135],"flexible":[16],"controllable":[17,56],"frameworks":[18],"is":[19],"increasing.":[20],"Although":[21],"existing":[22],"methods":[23],"can":[24],"guide":[25],"generation":[26,130],"beyond":[27],"text":[28,71],"prompts,":[29,72],"challenge":[31],"effectively":[33],"combining":[34],"multiple":[35],"conditional":[36],"inputs":[37],"while":[38],"maintaining":[39],"consistency":[40],"with":[41,141],"all":[42],"them":[44],"remains":[45],"unsolved.":[46],"To":[47],"address":[48],"this,":[49],"we":[50,79,102],"introduce":[51,80],"UniCombine,":[52],"a":[53,81,89,104],"DiT-based":[54],"multi-conditional":[55,115,129],"generative":[57,116],"framework":[58],"capable":[59],"handling":[61],"any":[62],"combination":[63],"conditions,":[65],"including":[66],"but":[67],"not":[68],"limited":[69],"to":[70,93,107],"spatial":[73],"maps,":[74],"subject":[76],"images.":[77],"Specifically,":[78],"novel":[82],"Conditional":[83],"MMDiT":[84],"Attention":[85],"mechanism":[86],"incorporate":[88],"trainable":[90],"LoRA":[91],"module":[92],"build":[94],"both":[95,119],"training-free":[97],"training-based":[99],"versions.":[100],"Additionally,":[101],"propose":[103],"new":[105],"pipeline":[106],"construct":[108],"SubjectSpatial200K,":[109],"first":[111],"dataset":[112],"designed":[113],"tasks":[117],"covering":[118],"subject-driven":[121],"spatially-aligned":[123],"conditions.":[124],"Extensive":[125],"experimental":[126],"results":[127],"on":[128],"demonstrate":[131],"outstanding":[133],"universality":[134],"capability":[137],"our":[139],"approach":[140],"state-of-the-art":[142],"performance.":[143]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-13T00:00:00"}