{"id":"https://openalex.org/W7137978937","doi":"https://doi.org/10.1609/aaai.v40i14.38151","title":"MagicPaint: Operate Anything for Image Inpainting with Diffusion Model","display_name":"MagicPaint: Operate Anything for Image Inpainting with Diffusion Model","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137978937","doi":"https://doi.org/10.1609/aaai.v40i14.38151"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i14.38151","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38151","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i14.38151","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129750622","display_name":"Qinhong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinhong Yang","raw_affiliation_strings":["University of Science and Technology of China\nAnhui Province Key Laboratory of Digital Security"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China\nAnhui Province Key Laboratory of Digital Security","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129702979","display_name":"Dongdong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Dongdong Chen","raw_affiliation_strings":["Microsoft CoreAI"],"affiliations":[{"raw_affiliation_string":"Microsoft CoreAI","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129725668","display_name":"Qi Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chu","raw_affiliation_strings":["University of Science and Technology of China\nAnhui Province Key Laboratory of Digital Security"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China\nAnhui Province Key Laboratory of Digital Security","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129672311","display_name":"Tao Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Gong","raw_affiliation_strings":["University of Science and Technology of China\nAnhui Province Key Laboratory of Digital Security"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China\nAnhui Province Key Laboratory of Digital Security","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129662415","display_name":"Qiankun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiankun Liu","raw_affiliation_strings":["University of Science and Technology Beijing"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123644644","display_name":"Zhentao Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhentao Tan","raw_affiliation_strings":["Independent Researcher"],"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129713284","display_name":"Xulin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xulin Li","raw_affiliation_strings":["University of Science and Technology of China\nAnhui Province Key Laboratory of Digital Security"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China\nAnhui Province Key Laboratory of Digital Security","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129651487","display_name":"Huamin Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I202334528","display_name":"Beijing Electronic Science and Technology Institute","ror":"https://ror.org/01xdzh226","country_code":"CN","type":"education","lineage":["https://openalex.org/I202334528"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huamin Feng","raw_affiliation_strings":["Beijing Electronic Science and Technology Institute"],"affiliations":[{"raw_affiliation_string":"Beijing Electronic Science and Technology Institute","institution_ids":["https://openalex.org/I202334528"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129724485","display_name":"Nenghai Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nenghai Yu","raw_affiliation_strings":["University of Science and Technology of China\nAnhui Province Key Laboratory of Digital Security"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China\nAnhui Province Key Laboratory of Digital Security","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5129750622"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24477612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"14","first_page":"11667","last_page":"11675"},"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":0.9578999876976013,"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":0.9578999876976013,"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":0.01759999990463257,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.0027000000700354576,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.9818999767303467},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6351000070571899},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.579200029373169},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.46299999952316284},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4392000138759613},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3345000147819519},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.334199994802475}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.9818999767303467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7114999890327454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6956999897956848},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6523000001907349},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6351000070571899},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.579200029373169},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.32580000162124634},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C200873422","wikidata":"https://www.wikidata.org/wiki/Q5448821","display_name":"Filling-in","level":2,"score":0.2847000062465668}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i14.38151","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38151","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i14.38151","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38151","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"diffusion-based":[1,41],"models":[2],"have":[3],"significantly":[4,145],"improved":[5],"inpainting":[6,14,42,51,86,109,122,142],"quality.":[7],"However,":[8],"existing":[9,108,148,219],"methods":[10],"struggle":[11],"with":[12,210],"multi-task":[13,114],"due":[15],"to":[16,26,139,165,218],"conflicting":[17,74],"optimization":[18,75],"objectives,":[19],"and":[20,49,55,63,77,97,115,144,159,184,204,207,214],"current":[21],"datasets":[22,110],"are":[23,111],"typically":[24],"limited":[25],"task-specific":[27],"scenarios,":[28,117],"hindering":[29],"joint":[30],"training.":[31],"To":[32],"address":[33],"these":[34],"challenges,":[35],"we":[36,125],"propose":[37],"MagicPaint,":[38],"a":[39,84,99,128,182],"unified":[40,185],"model":[43,158],"that":[44,190],"supports":[45],"object":[46,152,205],"addition,":[47,107,201,203],"removal,":[48],"unconditional":[50],"across":[52,195],"both":[53,157],"text":[54,177],"image":[56,133,179],"modalities.":[57],"MagicPaint":[58,162,191],"semantically":[59],"decouples":[60],"operation":[61],"types":[62],"target":[64],"content":[65,171],"by":[66],"learnable":[67],"tokens":[68],"in":[69,151,181],"MMToken":[70],"Module,":[71],"effectively":[72],"reconciling":[73],"objectives":[76],"enabling":[78],"robust":[79],"multi-task,":[80],"multi-modal":[81,116],"inpainting.":[82],"Besides,":[83],"novel":[85],"paradigm":[87],"named":[88],"MagicMask,":[89],"encodes":[90],"operating":[91],"intent":[92],"directly":[93],"into":[94],"the":[95,119],"mask":[96,100],"applies":[98],"loss":[101],"for":[102,113],"spatially":[103],"precise":[104],"supervision.":[105],"In":[106],"insufficient":[112],"limiting":[118],"capability":[120],"of":[121],"models.":[123],"Thus,":[124],"further":[126],"introduce":[127],"new":[129],"dataset":[130],"comprising":[131],"2.1M":[132],"tuples.":[134],"It":[135],"is":[136,173],"dedicatedly":[137],"designed":[138],"support":[140],"diverse":[141],"scenarios":[143],"improves":[146],"upon":[147],"datasets,":[149],"particularly":[150],"removal.":[153],"Through":[154],"efforts":[155],"from":[156],"data":[160],"perspectives,":[161],"enables":[163],"users":[164],"operate":[166],"anything\u2014add,":[167],"remove":[168],"or":[169,178],"inpaint":[170],"which":[172],"specified":[174],"through":[175],"either":[176],"modalities":[180],"seamless":[183],"manner.":[186],"Extensive":[187],"experiments":[188],"demonstrate":[189],"achieves":[192],"state-of-the-art":[193],"performance":[194],"three":[196],"key":[197],"tasks":[198],"(i.e.,":[199],"text-guided":[200],"image-guided":[202],"removal)":[206],"produces":[208],"outputs":[209],"superior":[211],"visual":[212],"consistency":[213],"contextual":[215],"fidelity":[216],"compared":[217],"methods.":[220]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}