{"id":"https://openalex.org/W4416690956","doi":"https://doi.org/10.1109/tpami.2025.3636582","title":"FreeEdit: Mask-Free Reference-Based Image Editing With Multi-Modal Instruction","display_name":"FreeEdit: Mask-Free Reference-Based Image Editing With Multi-Modal Instruction","publication_year":2025,"publication_date":"2025-11-24","ids":{"openalex":"https://openalex.org/W4416690956","doi":"https://doi.org/10.1109/tpami.2025.3636582","pmid":"https://pubmed.ncbi.nlm.nih.gov/41284388"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3636582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3636582","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101275668","display_name":"Runze He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Runze He","raw_affiliation_strings":["Chinese Academy of Sciences Institute of Information Engineering, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Institute of Information Engineering, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Ma","orcid":"https://orcid.org/0009-0003-4683-2726"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Ma","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103005183","display_name":"Linjiang Huang","orcid":"https://orcid.org/0000-0001-9701-6487"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linjiang Huang","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024226895","display_name":"Shaofei Huang","orcid":"https://orcid.org/0000-0001-8996-9907"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Huang","raw_affiliation_strings":["Chinese Academy of Sciences Institute of Information Engineering, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Institute of Information Engineering, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076814111","display_name":"Jialin Gao","orcid":"https://orcid.org/0000-0002-8554-7827"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialin Gao","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoming Wei","orcid":"https://orcid.org/0000-0002-7471-8344"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Wei","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031794241","display_name":"Jiao Dai","orcid":"https://orcid.org/0000-0003-3559-8009"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiao Dai","raw_affiliation_strings":["Chinese Academy of Sciences Institute of Information Engineering, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Institute of Information Engineering, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112539471","display_name":"Jizhong Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jizhong Han","raw_affiliation_strings":["Chinese Academy of Sciences Institute of Information Engineering, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Institute of Information Engineering, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101275668"],"corresponding_institution_ids":["https://openalex.org/I4210156404"],"apc_list":null,"apc_paid":null,"fwci":2.4362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91232061,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"48","issue":"3","first_page":"3319","last_page":"3334"},"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":0.7206000089645386,"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":0.7206000089645386,"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":0.08299999684095383,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.01600000075995922,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.8830000162124634},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5103999972343445},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5060999989509583},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4875999987125397},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42980000376701355},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.38679999113082886},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.3765999972820282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8834999799728394},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.8830000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6220999956130981},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5364999771118164},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3434000015258789},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3231000006198883},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26170000433921814}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3636582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3636582","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41284388","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41284388","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1981239318","display_name":null,"funder_award_id":"62461160308","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2558812161","display_name":null,"funder_award_id":"U23B2010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6362528638","display_name":null,"funder_award_id":"62576024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6436605283","display_name":null,"funder_award_id":"QY25227","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2962770929","https://openalex.org/W3096831136","https://openalex.org/W3159481202","https://openalex.org/W3173998882","https://openalex.org/W4288083516","https://openalex.org/W4312358791","https://openalex.org/W4312383858","https://openalex.org/W4312497550","https://openalex.org/W4312933868","https://openalex.org/W4382462760","https://openalex.org/W4386057725","https://openalex.org/W4386071613","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4386076425","https://openalex.org/W4386076532","https://openalex.org/W4386083141","https://openalex.org/W4386083151","https://openalex.org/W4386113271","https://openalex.org/W4390692030","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4390874393","https://openalex.org/W4390874575","https://openalex.org/W4402716223","https://openalex.org/W4402727613","https://openalex.org/W4402753899","https://openalex.org/W4402774219","https://openalex.org/W4403780582","https://openalex.org/W4403888423","https://openalex.org/W4404024902","https://openalex.org/W4404612908","https://openalex.org/W4404726022","https://openalex.org/W4413147134","https://openalex.org/W4413158163","https://openalex.org/W4414687714","https://openalex.org/W4415796438"],"related_works":[],"abstract_inverted_index":{"Introducing":[0],"user-specified":[1],"visual":[2,39],"concepts":[3,12],"in":[4,115,141],"image":[5,32,44,112,133,143,178],"editing":[6,64,72,79,113,134,171,210],"is":[7,98],"highly":[8],"practical":[9],"as":[10,173,175,190],"these":[11],"convey":[13],"the":[14,38,42,53,63,71,75,83,90,111,122,139,164,181,184,221],"user's":[15],"intent":[16],"more":[17],"precisely":[18],"than":[19],"text-based":[20],"descriptions.":[21],"We":[22,215],"propose":[23],"FreeEdit,":[24],"a":[25,107,116,147,152,157,176],"novel":[26],"approach":[27,51],"for":[28,77,131],"achieving":[29],"such":[30,189],"reference-based":[31,132],"editing,":[33,169],"which":[34],"can":[35],"accurately":[36],"reproduce":[37],"concept":[40],"from":[41],"reference":[43,86,103,148,177],"based":[45],"on":[46,200],"user-friendly":[47],"language":[48,59,213],"instructions.":[49,214],"Our":[50],"leverages":[52],"multi-modal":[54],"instruction":[55],"encoder":[56],"to":[57,61,100,138,219],"encode":[58],"instructions":[60],"guide":[62],"process.":[65],"This":[66,96],"implicit":[67],"way":[68,118],"of":[69,85,183,223],"locating":[70],"area":[73],"eliminates":[74],"need":[76],"manual":[78],"masks.":[80],"To":[81],"enhance":[82],"reconstruction":[84],"details,":[87],"we":[88,150],"introduce":[89],"Decoupled":[91],"Residual":[92],"Refer-Attention":[93],"(DRRA)":[94],"module.":[95],"module":[97],"designed":[99],"integrate":[101],"fine-grained":[102],"features":[104],"extracted":[105],"by":[106,203],"detail":[108],"extractor":[109],"into":[110],"process":[114],"residual":[117],"without":[119],"interfering":[120],"with":[121],"original":[123],"self-attention.":[124],"Given":[125],"that":[126,145,179],"existing":[127,233],"datasets":[128],"are":[129],"unsuitable":[130],"tasks,":[135],"particularly":[136],"due":[137],"difficulty":[140],"constructing":[142],"triplets":[144],"include":[146],"image,":[149],"curate":[151],"high-quality":[153,208],"dataset,":[154],"FreeBench,":[155],"using":[156],"newly":[158],"developed":[159],"twice-repainting":[160],"scheme.":[161],"FreeBench":[162,201],"comprises":[163],"images":[165],"before":[166],"and":[167,194],"after":[168],"detailed":[170],"instructions,":[172],"well":[174],"maintains":[180],"identity":[182],"edited":[185],"object,":[186],"encompassing":[187],"tasks":[188],"object":[191],"addition,":[192],"replacement,":[193],"deletion.":[195],"By":[196],"conducting":[197],"phased":[198],"training":[199],"followed":[202],"quality":[204],"tuning,":[205],"FreeEdit":[206,224],"achieves":[207],"zero-shot":[209],"through":[211],"convenient":[212],"conduct":[216],"extensive":[217],"experiments":[218],"evaluate":[220],"effectiveness":[222],"across":[225],"multiple":[226],"task":[227],"types,":[228],"demonstrating":[229],"its":[230],"superiority":[231],"over":[232],"methods.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-25T00:00:00"}