{"id":"https://openalex.org/W4415709070","doi":"https://doi.org/10.1109/icme59968.2025.11209148","title":"DPDEdit: Detail-Preserved Diffusion Models for Multimodal Fashion Image Editing","display_name":"DPDEdit: Detail-Preserved Diffusion Models for Multimodal Fashion Image Editing","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709070","doi":"https://doi.org/10.1109/icme59968.2025.11209148"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5086905501","display_name":"Xiaolong Wang","orcid":"https://orcid.org/0000-0003-4837-2586"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Wang","raw_affiliation_strings":["Shenzhen Technology University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University,China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058898461","display_name":"Zhi-Qi Cheng","orcid":"https://orcid.org/0000-0002-1720-2085"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiqi Cheng","raw_affiliation_strings":["University of Washington,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440604","display_name":"Jue Wang","orcid":"https://orcid.org/0000-0002-3641-3136"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jue Wang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huizi Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huizi Xue","raw_affiliation_strings":["Shenzhen Technology University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University,China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033413473","display_name":"Xiaojiang Peng","orcid":"https://orcid.org/0000-0002-5783-321X"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojiang Peng","raw_affiliation_strings":["Shenzhen Technology University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University,China","institution_ids":["https://openalex.org/I4210152380"]}]}],"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":false,"cited_by_count":1,"citation_normalized_percentile":null,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9897000193595886,"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":0.9897000193595886,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.002400000113993883,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.0010999999940395355,"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/image-editing","display_name":"Image editing","score":0.8996000289916992},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.611299991607666},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5317000150680542},{"id":"https://openalex.org/keywords/texture-synthesis","display_name":"Texture synthesis","score":0.46860000491142273},{"id":"https://openalex.org/keywords/image-texture","display_name":"Image texture","score":0.45680001378059387},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.44760000705718994}],"concepts":[{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.8996000289916992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868000268936157},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.611299991607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5777000188827515},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.46860000491142273},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4611000120639801},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.45680001378059387},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4025000035762787},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C200585589","wikidata":"https://www.wikidata.org/wiki/Q752176","display_name":"Texture mapping","level":2,"score":0.26589998602867126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2963876278","https://openalex.org/W2964318046","https://openalex.org/W3159481202","https://openalex.org/W3173998882","https://openalex.org/W4286611269","https://openalex.org/W4312933868","https://openalex.org/W4319300603","https://openalex.org/W4385896680","https://openalex.org/W4386076406","https://openalex.org/W4390873520","https://openalex.org/W4390874575","https://openalex.org/W4393159719","https://openalex.org/W4402547381"],"related_works":[],"abstract_inverted_index":{"Fashion":[0],"image":[1,22,53,158],"editing":[2,23,30,54,65,73],"is":[3],"a":[4,49,90,99,131],"crucial":[5],"tool":[6],"for":[7],"designers":[8],"to":[9,27,70,103,115,136],"convey":[10],"their":[11],"creative":[12],"ideas":[13],"by":[14],"visualizing":[15],"design":[16],"concepts":[17],"interactively.":[18],"However,":[19],"current":[20],"fashion":[21,52],"techniques":[24],"often":[25],"struggle":[26],"accurately":[28],"identify":[29],"regions":[31],"and":[32,93,107,110,143,160],"preserve":[33,116],"the":[34,64,72,77,80,85,117,127,163],"desired":[35],"garment":[36,82,122],"texture":[37,83,91,108,141],"detail.":[38],"To":[39,61,75],"address":[40],"these":[41],"challenges,":[42],"we":[43,67,88,125],"present":[44],"Detail-Preserved":[45],"Diffusion":[46],"Models":[47],"(DPDEdit),":[48],"new":[50],"multimodal":[51,132,165],"architecture":[55],"based":[56],"on":[57],"latent":[58],"diffusion":[59],"models.":[60],"precisely":[62],"locate":[63],"region,":[66],"introduce":[68],"Grounded-SAM":[69],"predict":[71],"region.":[74],"transfer":[76],"detail":[78],"of":[79,120,157],"given":[81,164],"into":[84],"target":[86],"image,":[87],"propose":[89],"injection":[92],"refinement":[94],"mechanism.":[95],"This":[96],"mechanism":[97],"employs":[98],"decoupled":[100],"cross-attention":[101],"layer":[102],"integrate":[104],"textual":[105,144],"descriptions":[106],"images,":[109],"incorporates":[111],"an":[112],"auxiliary":[113],"U-Net":[114],"high-frequency":[118],"details":[119],"generated":[121],"texture.":[123],"Additionally,":[124],"extend":[126],"VITON-HD":[128],"dataset":[129],"using":[130],"large":[133],"language":[134],"model":[135],"generate":[137],"paired":[138],"samples":[139],"with":[140,162],"images":[142],"descriptions.":[145],"Extensive":[146],"experiments":[147],"show":[148],"that":[149],"our":[150],"DPDEdit":[151],"outperforms":[152],"state-of-the-art":[153],"methods":[154],"in":[155],"terms":[156],"fidelity":[159],"coherence":[161],"input.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}