{"id":"https://openalex.org/W7156620680","doi":"https://doi.org/10.48550/arxiv.2604.23763","title":"Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing","display_name":"Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing","publication_year":2026,"publication_date":"2026-04-26","ids":{"openalex":"https://openalex.org/W7156620680","doi":"https://doi.org/10.48550/arxiv.2604.23763"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.23763","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23763","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.23763","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134785153","display_name":"Honghao Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Honghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127998090","display_name":"Xiangyuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiangyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134786682","display_name":"Yunhao Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Yunhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134789273","display_name":"Haohua Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Haohua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134817436","display_name":"Tianze Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Tianze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134780685","display_name":"Runqi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Runqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134809567","display_name":"Wei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134775202","display_name":"Yibo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134782038","display_name":"Xu Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134797354","display_name":"Yao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134804668","display_name":"Zhen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.5282999873161316,"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":0.5282999873161316,"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/T11019","display_name":"Image Enhancement Techniques","score":0.10329999774694443,"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":0.042100001126527786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.8810999989509583},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5012999773025513},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.4544000029563904},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4124999940395355},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.3073999881744385}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.8810999989509583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810699999332428},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5012999773025513},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2793000042438507},{"id":"https://openalex.org/C2776841711","wikidata":"https://www.wikidata.org/wiki/Q856","display_name":"Barcode","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.23763","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23763","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.23763","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23763","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"diffusion":[1],"transformers":[2],"(DiTs)":[3],"follow":[4],"global":[5],"editing":[6],"instructions":[7],"well":[8],"but":[9],"consistently":[10],"leak":[11],"local":[12,50],"edits":[13],"into":[14,47,91],"unrelated":[15],"regions,":[16],"because":[17],"joint-attention":[18],"architectures":[19],"offer":[20],"no":[21],"explicit":[22],"channel":[23],"telling":[24],"the":[25,30,87,92,97,100,104,111,115,122,135,139,144,209],"network":[26],"where":[27,78],"to":[28,73,79,103,166,183],"apply":[29],"edit.":[31],"We":[32,156],"introduce":[33],"AdaptEdit,":[34],"a":[35,44,48,66,83,107,128],"co-trained,":[36],"instruction-":[37],"and":[38,106,146,170,173,187,201],"region-aware":[39],"adapter":[40,88],"framework":[41],"that":[42,70],"retro-fits":[43],"frozen":[45],"DiT":[46],"precise":[49],"editor":[51,136],"without":[52],"modifying":[53],"its":[54],"backbone":[55],"weights.":[56],"A":[57,204],"lightweight":[58],"Block":[59],"Adapter":[60],"at":[61,154],"every":[62],"transformer":[63],"block":[64],"injects":[65],"structured":[67],"condition":[68],"stream":[69],"factorizes":[71],"what":[72],"edit":[74,80,93,140,171,181,190],"(instruction":[75],"semantics)":[76],"from":[77,143],"(spatial":[81],"mask);":[82],"learned":[84],"SpatialGate":[85],"routes":[86],"signal":[89],"selectively":[90],"region":[94,141],"while":[95],"keeping":[96],"rest":[98],"of":[99,211],"image":[101,148],"near-identical":[102],"source;":[105],"Region-Aware":[108],"Loss":[109],"focuses":[110],"training":[112],"objective":[113],"on":[114,158],"changing":[116],"pixels.":[117],"Because":[118],"these":[119],"components":[120],"make":[121],"backbone's":[123],"internal":[124],"representation":[125],"mask-aware":[126],"end-to-end,":[127],"thin":[129],"MaskPredictor":[130],"head":[131],"trained":[132],"jointly":[133],"with":[134],"can":[137],"ground":[138],"directly":[142],"instruction":[145,185],"source":[147],"--":[149],"eliminating":[150],"any":[151],"user-mask":[152],"requirement":[153],"deployment.":[155],"evaluate":[157],"two":[159],"complementary":[160],"benchmarks:":[161],"MagicBrush":[162],"(paired":[163],"ground-truth":[164,177],"targets)":[165],"measure":[167],"pixel-level":[168],"preservation":[169],"accuracy,":[172],"Emu-Edit":[174],"Test":[175],"(no":[176],"images,":[178],"9":[179],"diverse":[180],"categories)":[182],"stress-test":[184],"following":[186],"generalization":[188],"across":[189],"types.":[191],"On":[192],"both,":[193],"AdaptEdit":[194],"achieves":[195],"state-of-the-art":[196],"results,":[197],"simultaneously":[198],"outperforming":[199],"mask-free":[200],"oracle-mask":[202],"baselines.":[203],"seven-variant":[205],"ablation":[206],"cleanly":[207],"isolates":[208],"contribution":[210],"each":[212],"component.":[213]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-29T00:00:00"}