{"id":"https://openalex.org/W4415708988","doi":"https://doi.org/10.1109/icme59968.2025.11209192","title":"InpaintFormer: Prompt-guided High-Quality Face Inpainting with Mask-Aware Self-Attention","display_name":"InpaintFormer: Prompt-guided High-Quality Face Inpainting with Mask-Aware Self-Attention","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708988","doi":"https://doi.org/10.1109/icme59968.2025.11209192"},"language":"en","primary_location":{"id":"doi:10.1109/icme59968.2025.11209192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209192","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":"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/A5055605707","display_name":"Zhouhao Ouyang","orcid":"https://orcid.org/0000-0002-8179-875X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhouhao Ouyang","raw_affiliation_strings":["South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112538444","display_name":"Wen Xue","orcid":"https://orcid.org/0000-0002-0251-3489"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Xue","raw_affiliation_strings":["South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047762429","display_name":"Tianyi Chen","orcid":"https://orcid.org/0000-0002-9708-8939"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tianyi Chen","raw_affiliation_strings":["City University of Hong Kong,Department of Computer Science,Kowloon,Hong Kong"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Department of Computer Science,Kowloon,Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053838315","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0001-9136-195X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070982537","display_name":"Si Wu","orcid":"https://orcid.org/0000-0003-4022-0852"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Wu","raw_affiliation_strings":["South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107559842","display_name":"Yong Xu","orcid":"https://orcid.org/0009-0004-1113-8475"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science & Engineering,Guangzhou,P. R. China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004453915","display_name":"Patrick Le Callet","orcid":"https://orcid.org/0000-0002-2143-7063"},"institutions":[{"id":"https://openalex.org/I100445878","display_name":"\u00c9cole Centrale de Nantes","ror":"https://ror.org/03nh7d505","country_code":"FR","type":"education","lineage":["https://openalex.org/I100445878","https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick le Callet","raw_affiliation_strings":["Nantes université,Ecole Centrale Nantes,Nantes,France"],"affiliations":[{"raw_affiliation_string":"Nantes université,Ecole Centrale Nantes,Nantes,France","institution_ids":["https://openalex.org/I100445878"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001469325","display_name":"Dapeng Wu","orcid":"https://orcid.org/0000-0003-1755-0183"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dapeng Wu","raw_affiliation_strings":["City University of Hong Kong,Department of Computer Science,Kowloon,Hong Kong"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Department of Computer Science,Kowloon,Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5055605707"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31215405,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.807699978351593,"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":0.807699978351593,"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":0.16429999470710754,"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/T12301","display_name":"Facial Nerve Paralysis Treatment and Research","score":0.0034000000450760126,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.9373000264167786},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.552299976348877},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5335999727249146},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5113000273704529},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5019999742507935},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4163999855518341},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.40049999952316284},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.39649999141693115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3955000042915344}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.9373000264167786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7462999820709229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6796000003814697},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6586999893188477},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.552299976348877},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5113000273704529},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.29510000348091125},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.25130000710487366},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme59968.2025.11209192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209192","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"},{"id":"pmh:oai:HAL:hal-05579417v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05579417","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME), Jun 2025, Nantes, France. pp.1-6, ⟨10.1109/ICME59968.2025.11209192⟩","raw_type":"Conference papers"}],"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"},{"id":"https://openalex.org/F4320334111","display_name":"Innovation Fund","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W3136958399","https://openalex.org/W3167297682","https://openalex.org/W3180391059","https://openalex.org/W3199003182","https://openalex.org/W3203538104","https://openalex.org/W4312326192","https://openalex.org/W4312383858","https://openalex.org/W4312400623","https://openalex.org/W4313021454","https://openalex.org/W4386114505","https://openalex.org/W4386757817","https://openalex.org/W4393148226","https://openalex.org/W4402727769","https://openalex.org/W4402753670","https://openalex.org/W4404533930"],"related_works":[],"abstract_inverted_index":{"Face":[0],"image":[1,50,82,92,147],"inpainting,":[2,113],"especially":[3],"with":[4,69,97,149],"user-controllable":[5],"customization,":[6],"aims":[7],"to":[8,15,31,65,78,88,108,130],"restore":[9],"degraded":[10,110],"facial":[11],"regions":[12,111,132],"while":[13,114],"adhering":[14],"user-provided":[16],"instructions.":[17],"Traditional":[18],"inpainting":[19,51,125,148,162],"methods":[20,163],"often":[21],"focus":[22],"solely":[23],"on":[24],"restoring":[25],"visual":[26,67],"fidelity,":[27],"lacking":[28],"the":[29,90,98,121,124],"ability":[30],"incorporate":[32],"user":[33,70],"prompts":[34],"or":[35],"semantic":[36,95,153],"guidance.":[37],"In":[38],"this":[39],"work,":[40],"we":[41,57],"present":[42],"InpaintFormer,":[43],"a":[44,59,74,101,115],"novel":[45],"framework":[46],"for":[47,133],"user-controlled":[48],"face":[49,146],"guided":[52],"by":[53,72,127],"textual":[54],"prompts.":[55],"Specifically,":[56],"propose":[58],"Prompt-guided":[60],"Feature":[61],"Modulation":[62],"(PGFM)":[63],"module":[64],"align":[66],"features":[68],"instructions":[71],"utilizing":[73],"pre-trained":[75],"CLIP":[76],"model":[77],"extract":[79],"text":[80],"and":[81,141,152,168],"embeddings.":[83],"These":[84],"embeddings":[85],"are":[86],"fused":[87],"modulate":[89],"encoded":[91],"features,":[93],"ensuring":[94],"consistency":[96],"prompt.":[99],"Additionally,":[100],"Degradation":[102],"Mask":[103],"Predictor":[104],"(DMP)":[105],"is":[106],"introduced":[107],"identify":[109],"requiring":[112],"Mask-Aware":[116],"Self-Attention":[117],"(MASA)":[118],"mechanism":[119],"within":[120],"Transformer":[122],"refines":[123],"process":[126],"selectively":[128],"attending":[129],"non-degraded":[131],"generating":[134],"realistic":[135],"results.":[136],"By":[137],"combining":[138],"PGFM,":[139],"DMP,":[140],"MASA,":[142],"InpaintFormer":[143,159],"enables":[144],"controllable":[145],"high":[150],"fidelity":[151],"alignment.":[154],"Extensive":[155],"experiments":[156],"demonstrate":[157],"that":[158],"outperforms":[160],"state-of-the-art":[161],"in":[164],"terms":[165],"of":[166],"controllability":[167],"naturalness.":[169]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}