{"id":"https://openalex.org/W7204168137","doi":"https://doi.org/10.48550/arxiv.2608.23302","title":"Grounding Free-Form Instructions for Fashion Complementary Image Generation","display_name":"Grounding Free-Form Instructions for Fashion Complementary Image Generation","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204168137","doi":"https://doi.org/10.48550/arxiv.2608.23302"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23302","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23302","pdf_url":"https://arxiv.org/pdf/2608.23302","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.23302","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079764541","display_name":"Matteo Attimonelli","orcid":"https://orcid.org/0009-0003-6600-1938","observed_orcids":["https://orcid.org/0009-0003-6600-1938"]},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]},{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Attimonelli, Matteo","raw_affiliation_strings":["Politecnico di Bari , Italy","Sapienza University of Rome , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Bari , Italy","institution_ids":["https://openalex.org/I68618741"]},{"raw_affiliation_string":"Sapienza University of Rome , Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029434859","display_name":"Claudio Pomo","orcid":"https://orcid.org/0000-0001-5206-3909","observed_orcids":["https://orcid.org/0000-0001-5206-3909"]},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pomo, Claudio","raw_affiliation_strings":["Politecnico di Bari , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Bari , Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063449842","display_name":"Alessandro Bellis","orcid":"https://orcid.org/0000-0003-3476-5696","observed_orcids":["https://orcid.org/0000-0003-3476-5696"]},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"De Bellis, Alessandro","raw_affiliation_strings":["Politecnico di Bari , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Bari , Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094105787","display_name":"Danilo Danese","orcid":"https://orcid.org/0009-0000-5203-1229","observed_orcids":["https://orcid.org/0009-0000-5203-1229"]},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Danese, Danilo","raw_affiliation_strings":["Politecnico di Bari , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Bari , Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005545405","display_name":"Dietmar Jannach","orcid":"https://orcid.org/0000-0002-4698-8507","observed_orcids":["https://orcid.org/0000-0002-4698-8507"]},"institutions":[{"id":"https://openalex.org/I4210166741","display_name":"University of Klagenfurt","ror":"https://ror.org/05q9m0937","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210166741"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Jannach, Dietmar","raw_affiliation_strings":["University of Klagenfurt , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Klagenfurt , Austria","institution_ids":["https://openalex.org/I4210166741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034668928","display_name":"Tommaso Di Noia","orcid":"https://orcid.org/0000-0002-0939-5462","observed_orcids":["https://orcid.org/0000-0002-0939-5462"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Noia, Tommaso","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9955999851226807,"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":0.9955999851226807,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0038999998942017555,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/multimodal-grounding","display_name":"multimodal grounding","score":0.699999988079071},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.6449999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300999760627747},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6262000203132629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.604200005531311},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.593999981880188},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4896000027656555},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C530175646","wikidata":"https://www.wikidata.org/wiki/Q11460","display_name":"Clothing","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36419999599456787},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3273000121116638},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2605000138282776}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23302","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23302","pdf_url":"https://arxiv.org/pdf/2608.23302","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.23302","doi":"https://doi.org/10.48550/arxiv.2608.23302","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23302","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.23302","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23302","pdf_url":"https://arxiv.org/pdf/2608.23302","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204168137.pdf","grobid_xml":"https://content.openalex.org/works/W7204168137.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412588068","https://openalex.org/W7131099986","https://openalex.org/W3120946780","https://openalex.org/W7223464375","https://openalex.org/W4402696805","https://openalex.org/W2949653458","https://openalex.org/W4385810246","https://openalex.org/W4291219744","https://openalex.org/W4404782971","https://openalex.org/W2964318046"],"abstract_inverted_index":{"Fashion":[0],"complementary":[1,66],"image":[2,67,86,132,141],"generation":[3,68],"(CIG)":[4],"aims":[5],"to":[6,49,166],"create":[7],"garments":[8,157],"that":[9,126],"stylistically":[10,155],"match":[11],"a":[12,21,46,72,77,80,84,88,107,121,136],"seed":[13,85,131],"item":[14],"based":[15],"on":[16,38,129],"user":[17,52],"intent,":[18],"making":[19],"it":[20],"natural":[22,51],"multimodal":[23,73,138],"grounding":[24],"problem":[25],"where":[26,76],"models":[27],"must":[28],"interpret":[29],"language":[30],"in":[31],"visual":[32],"context.":[33],"Existing":[34],"CIG":[35,97],"benchmarks":[36,98],"rely":[37],"rigid":[39],"template":[40],"prompts":[41],"(e.g.,":[42],"\"a":[43],"photo":[44],"of":[45,60],"skirt\"),":[47],"failing":[48],"reflect":[50],"queries":[53],"and":[54,87,102,110,133,147,154,162],"obscuring":[55],"model":[56,78,109,125],"behavior":[57],"across":[58],"levels":[59],"linguistic":[61],"specificity.":[62],"We":[63,115],"introduce":[64],"fashion":[65],"with":[69,99,119],"free-form":[70],"instructions,":[71],"language-grounding":[74],"setting":[75],"generates":[79],"compatible":[81],"garment":[82],"from":[83],"natural-language":[89],"instruction.":[90],"To":[91],"this":[92],"end,":[93],"we":[94],"enrich":[95],"three":[96],"low-,":[100],"medium-,":[101],"high-specificity":[103],"instructions":[104],"generated":[105],"by":[106,112],"vision-language":[108],"validated":[111],"human":[113,148],"annotators.":[114],"instantiate":[116],"the":[117,130],"task":[118],"StyleFlow,":[120],"Rectified":[122],"Flow":[123],"Matching":[124],"jointly":[127],"conditions":[128],"instruction":[134],"within":[135],"single":[137],"transformer.":[139],"Across":[140],"quality":[142],"metrics,":[143],"catalog-alignment":[144],"analysis,":[145],"ablations,":[146],"evaluation,":[149],"StyleFlow":[150],"consistently":[151],"produces":[152],"instruction-aligned":[153],"coherent":[156],"while":[158],"reducing":[159],"architectural":[160],"complexity":[161],"inference":[163],"cost":[164],"relative":[165],"auxiliary-module":[167],"approaches.":[168]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}
