{"id":"https://openalex.org/W4387968172","doi":"https://doi.org/10.1145/3581783.3612137","title":"LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On","display_name":"LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968172","doi":"https://doi.org/10.1145/3581783.3612137"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612137","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612137","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612137","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612137","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048030317","display_name":"Davide Morelli","orcid":"https://orcid.org/0000-0001-7918-6220"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Davide Morelli","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008550420","display_name":"Alberto Baldrati","orcid":"https://orcid.org/0000-0002-5012-5800"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Baldrati","raw_affiliation_strings":["University of Florence, Florence, Italy"],"affiliations":[{"raw_affiliation_string":"University of Florence, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007384228","display_name":"Giuseppe Cartella","orcid":"https://orcid.org/0000-0002-5590-3253"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Cartella","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066519737","display_name":"Marcella Cornia","orcid":"https://orcid.org/0000-0001-9640-9385"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcella Cornia","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053986996","display_name":"Marco Bertini","orcid":"https://orcid.org/0000-0002-1364-218X"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Bertini","raw_affiliation_strings":["University of Florence, Florence, Italy"],"affiliations":[{"raw_affiliation_string":"University of Florence, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030948871","display_name":"Rita Cucchiara","orcid":"https://orcid.org/0000-0002-2239-283X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rita Cucchiara","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048030317"],"corresponding_institution_ids":["https://openalex.org/I122346577"],"apc_list":null,"apc_paid":null,"fwci":10.4888,"has_fulltext":true,"cited_by_count":89,"citation_normalized_percentile":{"value":0.98905143,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8580","last_page":"8589"},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9822999835014343,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9761999845504761,"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/computer-science","display_name":"Computer science","score":0.867955207824707},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5190873146057129},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.47137579321861267},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4597054421901703},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4587441384792328},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4515763819217682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4431111216545105},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43011415004730225},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4175548851490021},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2766943573951721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.867955207824707},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5190873146057129},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47137579321861267},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4597054421901703},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4587441384792328},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4515763819217682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4431111216545105},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43011415004730225},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4175548851490021},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2766943573951721},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3581783.3612137","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612137","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612137","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unimore.it:11380/1312086","is_oa":true,"landing_page_url":"https://hdl.handle.net/11380/1312086","pdf_url":"https://iris.unimore.it/bitstream/11380/1312086/6/3581783.3612137.pdf","source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arpi.unipi.it:11568/1275195","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1275195","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:flore.unifi.it:2158/1452879","is_oa":true,"landing_page_url":"https://hdl.handle.net/2158/1452879","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612137","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612137","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612137","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968172.pdf","grobid_xml":"https://content.openalex.org/works/W4387968172.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2130859329","https://openalex.org/W2133665775","https://openalex.org/W2200092826","https://openalex.org/W2331128040","https://openalex.org/W2471768434","https://openalex.org/W2772328249","https://openalex.org/W2883309205","https://openalex.org/W2912053445","https://openalex.org/W2962785568","https://openalex.org/W2962834855","https://openalex.org/W2964050021","https://openalex.org/W3013135579","https://openalex.org/W3110156989","https://openalex.org/W3159273905","https://openalex.org/W3172514680","https://openalex.org/W3173561538","https://openalex.org/W3173998882","https://openalex.org/W3175714707","https://openalex.org/W3189373506","https://openalex.org/W3198675127","https://openalex.org/W3212516020","https://openalex.org/W3216352822","https://openalex.org/W4210984894","https://openalex.org/W4213141551","https://openalex.org/W4224273707","https://openalex.org/W4282039370","https://openalex.org/W4286611269","https://openalex.org/W4292793879","https://openalex.org/W4292828922","https://openalex.org/W4292828970","https://openalex.org/W4312323657","https://openalex.org/W4312388283","https://openalex.org/W4312497550","https://openalex.org/W4312694728","https://openalex.org/W4312933868","https://openalex.org/W4313065289","https://openalex.org/W4319300603","https://openalex.org/W4386072096","https://openalex.org/W4386075631","https://openalex.org/W4386076425","https://openalex.org/W4386076532","https://openalex.org/W4386083141","https://openalex.org/W4390873520","https://openalex.org/W4390873539"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"The":[0,89],"rapidly":[1],"evolving":[2],"fields":[3],"of":[4,27,52,68,126,142,156,161],"e-commerce":[5],"and":[6,124,151,171,194],"metaverse":[7],"continue":[8],"to":[9,13,34,63,110,145],"seek":[10],"innovative":[11],"approaches":[12],"enhance":[14,111],"the":[15,19,25,66,77,85,112,116,122,127,139,143,146,163,179,190],"consumer":[16],"experience.":[17],"At":[18],"same":[20],"time,":[21],"recent":[22],"advancements":[23],"in":[24,47],"development":[26],"diffusion":[28,96],"models":[29,196],"have":[30],"enabled":[31],"generative":[32,71],"networks":[33],"create":[35],"remarkably":[36],"realistic":[37],"images.":[38],"In":[39],"this":[40],"context,":[41],"image-based":[42],"virtual":[43],"try-on,":[44],"which":[45],"consists":[46],"generating":[48],"a":[49,53,57,94,100,132,154,182,186],"novel":[50,101],"image":[51],"target":[54],"model":[55,83,97],"wearing":[56],"given":[58],"in-shop":[59,128],"garment,":[60,129],"has":[61],"yet":[62],"capitalize":[64],"on":[65,93,168],"potential":[67],"these":[69],"powerful":[70],"solutions.":[72],"This":[73],"work":[74],"introduces":[75],"LaDI-VTON,":[76],"first":[78],"Latent":[79],"Diffusion":[80],"textual":[81,133],"Inversion-enhanced":[82],"for":[84,189],"Virtual":[86],"Try-ON":[87],"task.":[88,191],"proposed":[90],"architecture":[91],"relies":[92],"latent":[95],"extended":[98],"with":[99],"additional":[102],"autoencoder":[103],"module":[104],"that":[105,136,175],"exploits":[106],"learnable":[107],"skip":[108],"connections":[109],"generation":[113,164],"process":[114],"preserving":[115],"model's":[117],"characteristics.":[118],"To":[119],"effectively":[120],"maintain":[121],"texture":[123],"details":[125],"we":[130],"propose":[131],"inversion":[134],"component":[135],"can":[137],"map":[138],"visual":[140],"features":[141],"garment":[144],"CLIP":[147],"token":[148,158],"embedding":[149],"space":[150],"thus":[152],"generate":[153],"set":[155],"pseudo-word":[157],"embeddings":[159],"capable":[160],"conditioning":[162],"process.":[165],"Experimental":[166],"results":[167],"Dress":[169],"Code":[170],"VITON-HD":[172],"datasets":[173],"demonstrate":[174],"our":[176],"approach":[177],"outperforms":[178],"competitors":[180],"by":[181],"consistent":[183],"margin,":[184],"achieving":[185],"significant":[187],"milestone":[188],"Source":[192],"code":[193],"trained":[195],"are":[197],"publicly":[198],"available":[199],"at:":[200],"https://github.com/miccunifi/ladi-vton.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":47},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}