{"id":"https://openalex.org/W7134046071","doi":"https://doi.org/10.1007/s11263-025-02694-y","title":"Disentangling Local and Global Semantics in Diffusion Models for Image Editing","display_name":"Disentangling Local and Global Semantics in Diffusion Models for Image Editing","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7134046071","doi":"https://doi.org/10.1007/s11263-025-02694-y"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02694-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02694-y","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s11263-025-02694-y","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027227399","display_name":"Manos Plitsis","orcid":null},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Manos Plitsis","raw_affiliation_strings":["Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Athens, Greece","Institute for Language and Speech Processing, Athena Research Center, Athens, Greece"],"raw_orcid":"https://orcid.org/0009-0008-8024-7033","affiliations":[{"raw_affiliation_string":"Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I200777214"]},{"raw_affiliation_string":"Institute for Language and Speech Processing, Athena Research Center, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013292648","display_name":"Theodoros Kouzelis","orcid":"https://orcid.org/0000-0002-1938-9250"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I4210130908","display_name":"Archimedia (Greece)","ror":"https://ror.org/04dxam533","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210130908"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Theodoros Kouzelis","raw_affiliation_strings":["Archimedes, Athena Research Center, Athens, Greece","Remote Sensing Laboratory, National Technical University of Athens, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Archimedes, Athena Research Center, Athens, Greece","institution_ids":["https://openalex.org/I4210130908","https://openalex.org/I4210156054"]},{"raw_affiliation_string":"Remote Sensing Laboratory, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051381280","display_name":"Panagiotis Koromilas","orcid":"https://orcid.org/0000-0002-4466-463X"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Panagiotis Koromilas","raw_affiliation_strings":["Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026317357","display_name":"Vassilis Katsouros","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vassilis Katsouros","raw_affiliation_strings":["Institute for Language and Speech Processing, Athena Research Center, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing, Athena Research Center, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017437981","display_name":"Mihalis A. Nicolaou","orcid":"https://orcid.org/0000-0001-9175-477X"},"institutions":[{"id":"https://openalex.org/I148518341","display_name":"Cyprus Institute","ror":"https://ror.org/01q8k8p90","country_code":"CY","type":"other","lineage":["https://openalex.org/I148518341"]},{"id":"https://openalex.org/I34771391","display_name":"University of Cyprus","ror":"https://ror.org/02qjrjx09","country_code":"CY","type":"education","lineage":["https://openalex.org/I34771391"]}],"countries":["CY"],"is_corresponding":false,"raw_author_name":"Mihalis A. Nicolaou","raw_affiliation_strings":["Computation-based Science and Technology Research Center, The Cyprus Institute, Nicosia, Cyprus","Department of Computer Science, University of Cyprus, Nicosia, Cyprus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computation-based Science and Technology Research Center, The Cyprus Institute, Nicosia, Cyprus","institution_ids":["https://openalex.org/I148518341"]},{"raw_affiliation_string":"Department of Computer Science, University of Cyprus, Nicosia, Cyprus","institution_ids":["https://openalex.org/I34771391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110767927","display_name":"Panagakis Yannis","orcid":null},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210130908","display_name":"Archimedia (Greece)","ror":"https://ror.org/04dxam533","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210130908"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yannis Panagakis","raw_affiliation_strings":["Archimedes, Athena Research Center, Athens, Greece","Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Archimedes, Athena Research Center, Athens, Greece","institution_ids":["https://openalex.org/I4210130908","https://openalex.org/I4210156054"]},{"raw_affiliation_string":"Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I200777214"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5027227399"],"corresponding_institution_ids":["https://openalex.org/I200777214","https://openalex.org/I4210098364"],"apc_list":{"value":3690,"currency":"USD","value_usd":3690},"apc_paid":{"value":3690,"currency":"USD","value_usd":3690},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25981518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":"4","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":0.9211000204086304,"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":0.9211000204086304,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.009200000204145908,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.008500000461935997,"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/semantics","display_name":"Semantics (computer science)","score":0.6412000060081482},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6171000003814697},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6115000247955322},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6110000014305115},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4595000147819519},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4507000148296356},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43230000138282776},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4156000018119812},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.319599986076355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980999946594238},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6412000060081482},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6171000003814697},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6115000247955322},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6110000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5889000296592712},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3131999969482422},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.26649999618530273},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2599000036716461},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2578999996185303},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-025-02694-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02694-y","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-025-02694-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02694-y","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W2065760681","https://openalex.org/W2963346868","https://openalex.org/W2969985801","https://openalex.org/W3034431451","https://openalex.org/W3096831136","https://openalex.org/W3216352822","https://openalex.org/W3217030260","https://openalex.org/W4312705932","https://openalex.org/W4312933868","https://openalex.org/W4386057725","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4390873489","https://openalex.org/W4394597158","https://openalex.org/W4400527815","https://openalex.org/W4402753991","https://openalex.org/W4415798294"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Diffusion":[1],"models":[2,88],"have":[3],"achieved":[4],"state-of-the-art":[5,200],"image":[6,19,82,103,178],"synthesis,":[7],"yet":[8],"unlike":[9],"GANs,":[10],"they":[11,50],"lack":[12],"a":[13,105,122,175],"well-structured":[14],"latent":[15,98,124,139],"space":[16],"for":[17,80],"intuitive":[18],"editing.":[20],"Existing":[21],"diffusion-based":[22],"editing":[23,83],"methods":[24],"often":[25],"rely":[26],"on":[27,53,187],"supervised":[28],"fine-tuning":[29],"or":[30,45,64],"text-based":[31],"guidance,":[32],"while":[33],"recent":[34],"unsupervised":[35,78],"techniques":[36],"leveraging":[37],"the":[38,96,113],"model\u2019s":[39,97],"bottleneck":[40],"layer":[41],"suffer":[42],"from":[43,174],"one":[44,158],"more":[46,195],"key":[47],"limitations:":[48],"(i)":[49],"focus":[51],"only":[52],"global":[54,62,93],"attributes,":[55],"(ii)":[56],"fail":[57],"to":[58,117,121,137,165],"disentangle":[59],"local":[60,91,143],"and":[61,92,104,134,179],"semantics,":[63],"(iii)":[65],"require":[66],"extensive":[67],"human":[68,184],"intervention.":[69],"To":[70],"fill":[71],"this":[72,129],"gap,":[73],"we":[74],"first":[75],"propose":[76],"an":[77,101],"method":[79,164,193],"localized":[81],"in":[84,95],"pre-trained":[85],"unconditional":[86],"diffusion":[87],"that":[89,119,141,191],"disentangles":[90],"semantics":[94],"space.":[99],"Given":[100],"input":[102],"user-specified":[106],"region":[107,120,181],"of":[108],"interest,":[109],"our":[110,163,192],"approach":[111],"uses":[112],"denoising":[114],"network\u2019s":[115],"Jacobian":[116],"map":[118],"corresponding":[123],"subspace.":[125],"We":[126,156],"then":[127],"separate":[128],"subspace":[130],"into":[131],"shared":[132],"(global)":[133],"region-specific":[135],"components":[136],"uncover":[138],"directions":[140,146,173],"control":[142],"attributes.":[144],"These":[145],"generalize":[147],"across":[148],"images,":[149],"enabling":[150],"semantically":[151],"consistent":[152],"edits":[153,198],"without":[154,183],"retraining.":[155],"go":[157],"step":[159],"further":[160],"by":[161,169],"extending":[162],"minimize":[166],"manual":[167],"supervision":[168],"automatically":[170],"inferring":[171],"edit":[172],"single":[176],"reference":[177],"generating":[180],"masks":[182],"input.":[185],"Experiments":[186],"multiple":[188],"datasets":[189],"show":[190],"yields":[194],"localized,":[196],"high-fidelity":[197],"than":[199],"approaches.":[201]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-03-07T00:00:00"}
