{"id":"https://openalex.org/W7147067602","doi":"https://doi.org/10.48550/arxiv.2603.29029","title":"MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation","display_name":"MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7147067602","doi":"https://doi.org/10.48550/arxiv.2603.29029"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.29029","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29029","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.29029","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124435525","display_name":"Bharath Krishnamurthy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krishnamurthy, Bharath","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081904333","display_name":"Ajita Rattani","orcid":"https://orcid.org/0000-0002-1541-8202"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rattani, Ajita","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"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":null,"last_page":null},"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":0.5227000117301941,"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":0.5227000117301941,"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/T11448","display_name":"Face recognition and analysis","score":0.4526999890804291,"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/T11019","display_name":"Image Enhancement Techniques","score":0.0019000000320374966,"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/fidelity","display_name":"Fidelity","score":0.4799000024795532},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.46399998664855957},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44029998779296875},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4390999972820282},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.42340001463890076},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.42160001397132874},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.3995000123977661},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.3855000138282776},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.3846000134944916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251999974250793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5084999799728394},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44029998779296875},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3855000138282776},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3285999894142151},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3012000024318695},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C135798126","wikidata":"https://www.wikidata.org/wiki/Q2167279","display_name":"Top-down and bottom-up design","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.29029","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29029","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":"doi:10.48550/arxiv.2603.29029","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29029","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"multimodal":[1,30,107,197],"face":[2,108,162,198],"generation":[3,199],"models":[4,13],"address":[5],"the":[6],"spatial":[7,19,94,121,179],"control":[8,57],"limitations":[9],"of":[10],"text-to-image":[11,52],"diffusion":[12,102],"by":[14,54],"augmenting":[15],"text-based":[16],"conditioning":[17],"with":[18,36],"priors":[20,154],"such":[21],"as":[22],"segmentation":[23],"masks,":[24],"sketches,":[25],"or":[26,59,80],"edge":[27],"maps.":[28],"This":[29,140],"fusion":[31,90],"enables":[32,169],"controllable":[33,161,208],"synthesis":[34],"aligned":[35],"both":[37,150],"high-level":[38],"semantic":[39,92,124],"intent":[40],"and":[41,74,93,123,145,152,191,213],"low-level":[42],"structural":[43,153],"layout.":[44],"However,":[45],"most":[46],"existing":[47],"approaches":[48],"typically":[49],"extend":[50],"pre-trained":[51],"pipelines":[53],"appending":[55],"auxiliary":[56],"modules":[58],"stitching":[60],"together":[61],"separate":[62],"uni-modal":[63],"networks.":[64],"These":[65],"ad":[66],"hoc":[67],"designs":[68],"inherit":[69],"architectural":[70],"constraints,":[71],"duplicate":[72],"parameters,":[73],"often":[75],"fail":[76],"under":[77],"conflicting":[78],"modalities":[79],"mismatched":[81],"latent":[82],"spaces,":[83],"limiting":[84],"their":[85],"ability":[86],"to":[87,149,155,174,177],"perform":[88],"synergistic":[89,106],"across":[91],"domains.":[95],"We":[96],"introduce":[97],"MMFace-DiT,":[98],"a":[99,115,133,165,170,185,202],"unified":[100],"dual-stream":[101,116],"transformer":[103,117],"engineered":[104],"for":[105,160,206],"synthesis.":[109],"Its":[110],"core":[111],"novelty":[112],"lies":[113],"in":[114,127,188],"block":[118],"that":[119],"processes":[120],"(mask/sketch)":[122],"(text)":[125],"tokens":[126],"parallel,":[128],"deeply":[129],"fusing":[130],"them":[131],"through":[132],"shared":[134],"Rotary":[135],"Position-Embedded":[136],"(RoPE)":[137],"Attention":[138],"mechanism.":[139],"design":[141],"prevents":[142],"modal":[143],"dominance":[144],"ensures":[146],"strong":[147],"adherence":[148],"text":[151],"achieve":[156],"unprecedented":[157],"spatial-semantic":[158],"consistency":[159],"generation.":[163],"Furthermore,":[164],"novel":[166],"Modality":[167],"Embedder":[168],"single":[171],"cohesive":[172],"model":[173],"dynamically":[175],"adapt":[176],"varying":[178],"conditions":[180],"without":[181],"retraining.":[182],"MMFace-DiT":[183],"achieves":[184],"40%":[186],"improvement":[187],"visual":[189],"fidelity":[190],"prompt":[192],"alignment":[193],"over":[194],"six":[195],"state-of-the-art":[196],"models,":[200],"establishing":[201],"flexible":[203],"new":[204],"paradigm":[205],"end-to-end":[207],"generative":[209],"modeling.":[210],"The":[211],"code":[212],"dataset":[214],"are":[215],"available":[216],"on":[217],"our":[218],"project":[219],"page:":[220],"https://vcbsl.github.io/MMFace-DiT/":[221]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-02T00:00:00"}