{"id":"https://openalex.org/W4405601632","doi":"https://doi.org/10.1109/ivcnz64857.2024.10794459","title":"MAC-VTON: Multi-modal Attention Conditioning for Virtual Try-on with Diffusion-Based Inpainting","display_name":"MAC-VTON: Multi-modal Attention Conditioning for Virtual Try-on with Diffusion-Based Inpainting","publication_year":2024,"publication_date":"2024-12-04","ids":{"openalex":"https://openalex.org/W4405601632","doi":"https://doi.org/10.1109/ivcnz64857.2024.10794459"},"language":"en","primary_location":{"id":"doi:10.1109/ivcnz64857.2024.10794459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ivcnz64857.2024.10794459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 39th International Conference on Image and Vision Computing New Zealand (IVCNZ)","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/A5104181705","display_name":"Sanhita Pathak","orcid":"https://orcid.org/0009-0002-9489-8386"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sanhita Pathak","raw_affiliation_strings":["BSTTM Indian Institute of Technology Delhi,New Delhi,India"],"affiliations":[{"raw_affiliation_string":"BSTTM Indian Institute of Technology Delhi,New Delhi,India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006877813","display_name":"Vinay Kaushik","orcid":"https://orcid.org/0000-0001-6729-4857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vinay Kaushik","raw_affiliation_strings":["IIIT Sonepat,Dept. of Computer Science Engineering,Sonepat,India"],"affiliations":[{"raw_affiliation_string":"IIIT Sonepat,Dept. of Computer Science Engineering,Sonepat,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066116024","display_name":"Brejesh Lall","orcid":"https://orcid.org/0000-0003-2677-3071"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Brejesh Lall","raw_affiliation_strings":["Indian Institute of Technology Delhi,Dept. of Electrical Engineering,New Delhi,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Delhi,Dept. of Electrical Engineering,New Delhi,India","institution_ids":["https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104181705"],"corresponding_institution_ids":["https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24312846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9894999861717224,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9437000155448914,"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/inpainting","display_name":"Inpainting","score":0.8234392404556274},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7246370315551758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6476208567619324},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5448609590530396},{"id":"https://openalex.org/keywords/conditioning","display_name":"Conditioning","score":0.48581647872924805},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3271212577819824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3074823021888733},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.16258195042610168},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13413971662521362},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10550013184547424},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10511663556098938}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.8234392404556274},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7246370315551758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6476208567619324},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5448609590530396},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.48581647872924805},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3271212577819824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3074823021888733},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.16258195042610168},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13413971662521362},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10550013184547424},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10511663556098938},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ivcnz64857.2024.10794459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ivcnz64857.2024.10794459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 39th International Conference on Image and Vision Computing New Zealand (IVCNZ)","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":20,"referenced_works":["https://openalex.org/W2991079364","https://openalex.org/W3035668851","https://openalex.org/W3173998882","https://openalex.org/W4292828922","https://openalex.org/W4312323657","https://openalex.org/W4312933868","https://openalex.org/W4313065289","https://openalex.org/W4386072096","https://openalex.org/W4386075533","https://openalex.org/W4386076406","https://openalex.org/W4387968172","https://openalex.org/W4393148714","https://openalex.org/W4402781001","https://openalex.org/W4402951553","https://openalex.org/W4402980545","https://openalex.org/W6796581206","https://openalex.org/W6847372442","https://openalex.org/W6855806805","https://openalex.org/W6859040496","https://openalex.org/W6863160814"],"related_works":["https://openalex.org/W2380775572","https://openalex.org/W2213520135","https://openalex.org/W2244018504","https://openalex.org/W4242046654","https://openalex.org/W3174923100","https://openalex.org/W3134074939","https://openalex.org/W2117562399","https://openalex.org/W4298074124","https://openalex.org/W2587407424","https://openalex.org/W1523707610"],"abstract_inverted_index":{"Virtual":[0],"try-on":[1,26,40,63,166],"has":[2],"emerged":[3],"as":[4],"a":[5,79],"prominent":[6],"field":[7],"of":[8,11,44,61,73,98],"research":[9],"because":[10],"its":[12],"wide":[13],"application":[14],"in":[15,20],"ecommerce.":[16],"The":[17,39],"key":[18],"challenge":[19],"this":[21,53],"task":[22],"is":[23,31,43],"producing":[24],"realistic":[25,50],"images,":[27],"where":[28],"the":[29,36,57,66,90,95,125,134],"garment":[30,115,126,155],"warped":[32],"to":[33,46,68,113,121,137],"accurately":[34],"fit":[35],"person's":[37],"body.":[38],"generation":[41],"quality":[42],"significance":[45],"provide":[47],"desirable":[48],"and":[49,59,118,127,157],"results.":[51],"In":[52],"work,":[54],"we":[55,77],"improve":[56],"realism":[58],"accuracy":[60],"virtual":[62,165],"by":[64],"enhancing":[65],"architecture":[67],"accept":[69],"attention":[70,92],"conditioning.":[71],"Instead":[72],"using":[74],"multiple":[75,99],"ControlNets,":[76],"introduce":[78],"novel":[80],"Multi":[81],"Zero":[82],"Cross":[83],"Residual":[84],"Attention":[85],"Block":[86],"(MZB)":[87],"that":[88],"replaces":[89],"standard":[91,164],"mechanism,":[93],"enabling":[94],"simultaneous":[96],"incorporation":[97],"conditioning":[100],"inputs.":[101],"These":[102],"include":[103],"DinoV2":[104],"embeddings":[105],"for":[106],"rich":[107],"semantic":[108],"cloth":[109],"representation,":[110],"color":[111,116],"histograms":[112],"preserve":[114],"fidelity,":[117],"skin":[119,129],"maps":[120],"ensure":[122],"coherence":[123],"between":[124],"exposed":[128],"areas.":[130],"This":[131],"design":[132],"allows":[133],"diffusion":[135],"model":[136],"effectively":[138],"handle":[139],"complex":[140],"garment-body":[141],"interactions":[142],"with":[143],"greater":[144],"precision.":[145],"Through":[146],"extensive":[147],"experiments,":[148],"our":[149],"method":[150],"demonstrates":[151],"superior":[152],"control":[153],"over":[154],"alignment":[156],"visual":[158],"realism,":[159],"achieving":[160],"competitive":[161],"results":[162],"on":[163],"benchmarks.":[167]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}