{"id":"https://openalex.org/W7131061914","doi":"https://doi.org/10.1109/iccvw69036.2025.00210","title":"MFT-VITON: High-Fidelity Virtual Try-On with Minimal Input via a Mask-Free Transformer-Diffusion Model","display_name":"MFT-VITON: High-Fidelity Virtual Try-On with Minimal Input via a Mask-Free Transformer-Diffusion Model","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131061914","doi":"https://doi.org/10.1109/iccvw69036.2025.00210"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00210","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 Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101304185","display_name":"Zhenchen Wan","orcid":"https://orcid.org/0009-0006-6550-1035"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zhenchen Wan","raw_affiliation_strings":["University of Melbourne"],"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126646456","display_name":"Yanwu Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanwu Xu","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126588931","display_name":"Dongting Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dongting Hu","raw_affiliation_strings":["University of Melbourne"],"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124160706","display_name":"W. Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weilun Cheng","raw_affiliation_strings":["University of Melbourne"],"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126640730","display_name":"Tianxi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tianxi Chen","raw_affiliation_strings":["University of Melbourne"],"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126631502","display_name":"Zhaoqing Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhaoqing Wang","raw_affiliation_strings":["The University of Sydney"],"affiliations":[{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083732181","display_name":"F. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["University of Melbourne"],"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tongliang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tongliang Liu","raw_affiliation_strings":["The University of Sydney"],"affiliations":[{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091227928","display_name":"Maoguo Gong","orcid":"https://orcid.org/0000-0002-0415-8556"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mingming Gong","raw_affiliation_strings":["University of Melbourne"],"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101304185"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65564719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2006","last_page":"2015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11263","display_name":"Electromagnetic Simulation and Numerical Methods","score":0.07689999788999557,"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"}},"topics":[{"id":"https://openalex.org/T11263","display_name":"Electromagnetic Simulation and Numerical Methods","score":0.07689999788999557,"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"}},{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.05860000103712082,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.04960000142455101,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/rendering","display_name":"Rendering (computer graphics)","score":0.5841000080108643},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.42829999327659607},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38199999928474426},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.3750999867916107},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3749000132083893},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.37439998984336853},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.36800000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813000082969666},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5841000080108643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722999930381775},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.37439998984336853},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00210","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 Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2962785568","https://openalex.org/W2963266880","https://openalex.org/W2964050021","https://openalex.org/W2979283733","https://openalex.org/W2981950698","https://openalex.org/W2991530302","https://openalex.org/W3035515747","https://openalex.org/W3053644769","https://openalex.org/W3092643288","https://openalex.org/W3153469116","https://openalex.org/W3162633357","https://openalex.org/W3173998882","https://openalex.org/W3204971388","https://openalex.org/W4200095354","https://openalex.org/W4292828922","https://openalex.org/W4312256012","https://openalex.org/W4312323657","https://openalex.org/W4312613780","https://openalex.org/W4312933868","https://openalex.org/W4313030876","https://openalex.org/W4313065289","https://openalex.org/W4385896680","https://openalex.org/W4386072096","https://openalex.org/W4386075533","https://openalex.org/W4386076406","https://openalex.org/W4387968172","https://openalex.org/W4393159179","https://openalex.org/W4402702915","https://openalex.org/W4402716473","https://openalex.org/W4402727504","https://openalex.org/W4402727781","https://openalex.org/W4403757521","https://openalex.org/W4404002698","https://openalex.org/W4409262010","https://openalex.org/W4413146255"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,37,188],"Virtual":[3],"Try-On":[4],"(VITON)":[5],"have":[6],"achieved":[7],"remarkable":[8],"realism":[9],"and":[10,41,102,112,128,150,170,192],"texture":[11],"fidelity,":[12],"largely":[13],"attributed":[14],"to":[15,97,146],"the":[16,117,161],"emergence":[17],"of":[18],"text-to-image":[19],"(T2I)":[20],"diffusion":[21],"models.":[22],"However,":[23],"prevailing":[24],"Unet-based":[25],"T2I":[26],"backbones":[27],"are":[28],"increasingly":[29],"inadequate":[30],"for":[31,89,106,154,163],"rendering":[32],"fine-grained":[33],"garment":[34,156,168],"details,":[35],"particularly":[36],"preserving":[38,167],"textual":[39,110],"elements":[40],"subtle":[42],"textures.":[43],"Diffusion":[44],"Transformer":[45],"(DiT)-based":[46],"architectures,":[47],"with":[48,81],"their":[49,58],"superior":[50],"generative":[51],"capacity,":[52],"offer":[53],"a":[54,76,85,93,138,143,185],"promising":[55],"alternative,":[56],"yet":[57],"integration":[59],"into":[60],"current":[61],"VITON":[62],"pipelines":[63],"is":[64],"impeded":[65],"by":[66,141],"substantial":[67],"architectural":[68],"mismatches.":[69],"To":[70,131],"address":[71],"these":[72,133],"challenges,":[73],"we":[74,135],"propose":[75],"novel":[77],"mask-based":[78,118,182],"framework":[79],"augmented":[80],"three":[82],"key":[83],"components:":[84],"Garment":[86],"Semantic":[87],"(GS)-Adapter":[88],"enhanced":[90],"garment-specific":[91],"representation,":[92],"Text":[94],"Preservation":[95],"Loss":[96],"maintain":[98],"high-fidelity":[99],"text":[100],"rendering,":[101],"LLM-driven":[103],"semantic":[104],"guidance":[105],"improved":[107],"alignment":[108],"between":[109],"prompts":[111],"visual":[113,190],"outputs.":[114],"While":[115],"effective,":[116],"approach":[119,159],"still":[120],"relies":[121],"heavily":[122],"on":[123],"user-provided":[124],"masks,":[125],"introducing":[126],"complexity":[127],"potential":[129],"inaccuracies.":[130],"mitigate":[132],"issues,":[134],"further":[136],"develop":[137],"Mask-Free":[139,177],"strategy":[140],"leveraging":[142],"synthesized":[144],"dataset":[145],"adapt":[147],"our":[148,176],"model":[149,178],"other":[151],"mask-dependent":[152],"baselines":[153],"mask-independent":[155],"transfer.":[157],"This":[158],"eliminates":[160],"need":[162],"explicit":[164],"masks":[165],"while":[166],"shape":[169],"texture.":[171],"Experimental":[172],"results":[173],"demonstrate":[174],"that":[175],"consistently":[179],"outperforms":[180],"state-of-the-art":[181],"methods,":[183],"establishing":[184],"new":[186],"benchmark":[187],"both":[189],"fidelity":[191],"usability.":[193]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-02-24T00:00:00"}