{"id":"https://openalex.org/W4405094734","doi":"https://doi.org/10.1109/iccv51701.2025.01718","title":"CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation","display_name":"CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405094734","doi":"https://doi.org/10.1109/iccv51701.2025.01718"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01718","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/2412.03859","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110372095","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0001-9849-1327"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100893702","display_name":"Dexiang Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dexiang Hong","raw_affiliation_strings":["Bytedance Intelligent Creation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Intelligent Creation,China","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100650009","display_name":"Yitong Wang","orcid":"https://orcid.org/0000-0002-7559-4152"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yitong Wang","raw_affiliation_strings":["Bytedance Intelligent Creation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Intelligent Creation,China","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001847898","display_name":"Jie Shao","orcid":"https://orcid.org/0000-0001-7793-2031"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Shao","raw_affiliation_strings":["Bytedance Intelligent Creation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Intelligent Creation,China","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101918099","display_name":"Xinglong Wu","orcid":"https://orcid.org/0000-0001-9778-0864"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xinglong Wu","raw_affiliation_strings":["Bytedance Intelligent Creation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Intelligent Creation,China","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026167547","display_name":"Zuxuan Wu","orcid":"https://orcid.org/0000-0002-8689-5807"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I4210139618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I4210139618"]}]}],"institutions":[],"countries_distinct_count":2,"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":"18487","last_page":"18497"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8500000238418579,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8500000238418579,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.7645999789237976,"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/T14270","display_name":"Simulation and Modeling Applications","score":0.7621999979019165,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.5294009447097778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4450756013393402},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44381535053253174},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.31718602776527405},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.2751827836036682},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19981741905212402},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05609580874443054}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5294009447097778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4450756013393402},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44381535053253174},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31718602776527405},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2751827836036682},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19981741905212402},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05609580874443054}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01718","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:2412.03859","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03859","pdf_url":"https://arxiv.org/pdf/2412.03859","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.2412.03859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.03859","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:2412.03859","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03859","pdf_url":"https://arxiv.org/pdf/2412.03859","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/G472569701","display_name":null,"funder_award_id":"62032006","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":["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/W4396696052"],"abstract_inverted_index":{"Diffusion":[0,63],"models":[1,52,234],"have":[2,67],"been":[3,30],"recognized":[4],"for":[5,75,214,263],"their":[6],"ability":[7],"to":[8,32,38,84,106,131,147],"generate":[9],"images":[10],"that":[11,255],"are":[12],"not":[13],"only":[14],"visually":[15],"appealing":[16],"but":[17,80],"also":[18],"of":[19,87,121,128,231],"high":[20],"artistic":[21],"quality.":[22,219],"As":[23],"a":[24,125,159,176,197,201,211,252],"result,":[25],"Layout-to-Image":[26],"(L2I)":[27],"generation":[28,71,77,218,244],"has":[29,60],"proposed":[31],"leverage":[33],"region-specific":[34],"positions":[35],"and":[36,42,55,57,93,113,143,166,188,200,245,261],"descriptions":[37],"enable":[39],"more":[40],"precise":[41],"controllable":[43],"generation.":[44,266],"However,":[45],"previous":[46],"methods":[47],"primarily":[48],"focus":[49],"on":[50],"UNet-based":[51],"(\\eg":[53],"SD1.5":[54],"SDXL),":[56],"limited":[58],"effort":[59],"explored":[61],"Multimodal":[62],"Transformers":[64],"(MM-DiTs),":[65],"which":[66,182,226],"demonstrated":[68],"powerful":[69],"image":[70,142],"capabilities.":[72],"Enabling":[73],"MM-DiT":[74],"layout-to-image":[76,265],"seems":[78],"straightforward":[79],"is":[81,90,194],"challenging":[82],"due":[83],"the":[85,119,133,141,149,155,163,170,207,216,223,229,257],"complexity":[86],"how":[88],"layout":[89,109,178,236,243,258],"introduced,":[91],"integrated,":[92],"balanced":[94],"among":[95,151],"multiple":[96],"modalities.":[97,145],"To":[98,117],"this":[99],"end,":[100],"we":[101,123,153,174,221],"explore":[102],"various":[103],"network":[104,129],"variants":[105],"efficiently":[107],"incorporate":[108],"guidance":[110],"into":[111,158,228,240],"MM-DiT,":[112,122],"ultimately":[114],"present":[115],"SiamLayout.":[116],"inherit":[118],"advantages":[120],"use":[124],"separate":[126],"set":[127],"weights":[130],"process":[132],"layout,":[134],"treating":[135],"it":[136],"as":[137,140,210],"equally":[138],"important":[139],"text":[144],"Meanwhile,":[146],"alleviate":[148],"competition":[150],"modalities,":[152],"decouple":[154],"image-layout":[156],"interaction":[157],"siamese":[160],"branch":[161],"alongside":[162],"image-text":[164,186],"one":[165],"fuse":[167],"them":[168,239],"in":[169,235,242],"later":[171],"stage.":[172],"Moreover,":[173],"contribute":[175],"large-scale":[177],"dataset,":[179,260],"named":[180],"LayoutSAM,":[181],"includes":[183],"2.7":[184],"million":[185,190],"pairs":[187],"10.7":[189],"entities.":[191],"Each":[192],"entity":[193],"annotated":[195],"with":[196],"bounding":[198],"box":[199],"detailed":[202],"description.":[203],"We":[204],"further":[205],"construct":[206],"LayoutSAM-Eval":[208],"benchmark":[209],"comprehensive":[212],"tool":[213],"evaluating":[215],"L2I":[217],"Finally,":[220],"introduce":[222],"Layout":[224],"Designer,":[225],"taps":[227],"potential":[230],"large":[232],"language":[233],"planning,":[237],"transforming":[238],"experts":[241],"optimization.":[246],"These":[247],"components":[248],"form":[249],"CreatiLayout":[250],"--":[251],"systematic":[253],"solution":[254],"integrates":[256],"model,":[259],"planner":[262],"creative":[264]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}