{"id":"https://openalex.org/W7164499758","doi":"https://doi.org/10.1109/tip.2026.3685069","title":"Text-Driven Relation Manipulation of Diffusion Imagery","display_name":"Text-Driven Relation Manipulation of Diffusion Imagery","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7164499758","doi":"https://doi.org/10.1109/tip.2026.3685069","pmid":"https://pubmed.ncbi.nlm.nih.gov/42284165"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3685069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3685069","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Image Processing","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/A5100587789","display_name":"Yiming Li","orcid":"https://orcid.org/0009-0001-7862-840X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Li","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0009-0001-7862-840X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505982","display_name":"Peng Zhou","orcid":"https://orcid.org/0000-0002-0674-9296"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhou","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics"],"raw_orcid":"https://orcid.org/0000-0002-0674-9296","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007918444","display_name":"Hongwei Hu","orcid":"https://orcid.org/0000-0003-1284-1328"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongwei Hu","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138524001","display_name":"Xiaokang Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaokang Qin","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100945990","display_name":"Jun Sun","orcid":"https://orcid.org/0009-0001-1956-694X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Sun","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0009-0001-1956-694X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021424158","display_name":"Yan Xu","orcid":"https://orcid.org/0000-0002-3319-4695"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Xu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0000-0001-6508-4469","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64150359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"7475","last_page":"7490"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.19339999556541443,"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"}},"topics":[{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.19339999556541443,"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"}},{"id":"https://openalex.org/T10656","display_name":"Child and Animal Learning Development","score":0.03889999911189079,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.035999998450279236,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5867000222206116},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.47429999709129333},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4174000024795532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3264999985694885},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.30059999227523804},{"id":"https://openalex.org/keywords/surface-fitting","display_name":"Surface fitting","score":0.2833000123500824}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5867000222206116},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43479999899864197},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4327999949455261},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4174000024795532},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39739999175071716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3919000029563904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3240000009536743},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.30059999227523804},{"id":"https://openalex.org/C2984999661","wikidata":"https://www.wikidata.org/wiki/Q603159","display_name":"Surface fitting","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3685069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3685069","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Image Processing","raw_type":"journal-article"},{"id":"pmid:42284165","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42284165","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6360183275","display_name":null,"funder_award_id":"22DZ2229005","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G7976557715","display_name":null,"funder_award_id":"62171282","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2064076387","https://openalex.org/W2965289598","https://openalex.org/W2989265781","https://openalex.org/W3035515747","https://openalex.org/W3173102319","https://openalex.org/W3178406257","https://openalex.org/W3212516020","https://openalex.org/W3216352822","https://openalex.org/W4220794053","https://openalex.org/W4286611278","https://openalex.org/W4312282373","https://openalex.org/W4312420092","https://openalex.org/W4312497550","https://openalex.org/W4312824283","https://openalex.org/W4312931308","https://openalex.org/W4312933868","https://openalex.org/W4319299843","https://openalex.org/W4385270985","https://openalex.org/W4385271134","https://openalex.org/W4385271281","https://openalex.org/W4385682474","https://openalex.org/W4386057725","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4386076425","https://openalex.org/W4386076532","https://openalex.org/W4389205309","https://openalex.org/W4390871780","https://openalex.org/W4390872671","https://openalex.org/W4393154259","https://openalex.org/W4402660138","https://openalex.org/W4402774090","https://openalex.org/W4403998619","https://openalex.org/W4404965624","https://openalex.org/W4404984122","https://openalex.org/W7133185348","https://openalex.org/W7133210112"],"related_works":[],"abstract_inverted_index":{"Text-guided":[0],"image":[1,170,191],"manipulation":[2,51,164],"has":[3],"recently":[4],"attracted":[5],"significant":[6],"attention.":[7],"Prevailing":[8],"algorithms":[9],"predominantly":[10],"focus":[11],"on":[12],"modifying":[13,69],"the":[14,31,60,70,78,127,146,185],"appearances":[15],"of":[16,62,68,72,82,108,116,149,165,176],"existing":[17],"instances,":[18],"such":[19,41,161],"as":[20,42,162],"texture":[21],"and":[22,80,95,114,143,168,193,209],"attribute":[23],"editing,":[24],"while":[25],"they":[26],"often":[27],"fail":[28],"to":[29,125,139],"address":[30],"interactions":[32,83],"between":[33],"different":[34,174],"instances":[35,73],"or":[36],"achieve":[37],"fundamental":[38],"structural":[39],"changes,":[40],"multi-object":[43],"editing.":[44],"This":[45,64,199],"paper":[46],"introduces":[47],"a":[48,105,134,202],"novel":[49],"text-guided":[50],"task":[52,65],"named":[53],"\"relation":[54],"manipulation\",":[55],"aimed":[56],"at":[57,215],"fundamentally":[58],"altering":[59],"structure":[61],"images.":[63],"is":[66,213],"capable":[67],"quantity":[71],"and,":[74],"more":[75],"importantly,":[76],"enhancing":[77],"understanding":[79,113],"editing":[81],"among":[84],"diverse":[85],"instances.":[86],"Our":[87],"approach":[88,181],"comprises":[89],"two":[90],"main":[91],"components:":[92],"relation":[93,163],"customization":[94,100],"multi-region":[96,153],"guided":[97,120],"diffusion.":[98],"Relation":[99],"fine-tunes":[101],"specific":[102],"relationships":[103],"using":[104],"compact":[106],"dataset":[107],"exemplary":[109],"relations,":[110],"facilitating":[111],"nuanced":[112],"implementation":[115],"instance":[117],"interactions.":[118],"Multi-region":[119],"diffusion":[121],"employs":[122],"gradient":[123],"optimization":[124],"update":[126],"generation":[128,192],"process":[129],"across":[130],"multiple":[131],"regions,":[132],"integrating":[133],"fine-grained":[135],"attention":[136],"control":[137,195],"strategy":[138],"minimize":[140],"regional":[141],"interference":[142],"conflict.":[144],"Additionally,":[145],"demonstrated":[147],"applications":[148],"our":[150,180],"method":[151],"in":[152,158],"inversion":[154],"underline":[155],"its":[156],"potential":[157],"practical":[159],"scenarios,":[160],"real":[166],"images":[167],"consecutive":[169],"manipulation.":[171,198],"Compatible":[172],"with":[173],"variants":[175],"Stable":[177,186],"Diffusion":[178,187],"models,":[179],"seamlessly":[182],"integrates":[183],"into":[184],"WebUI,":[188],"enabling":[189],"high-quality":[190],"exceptional":[194],"over":[196],"extensive":[197],"makes":[200],"it":[201],"robust":[203],"tool":[204],"for":[205],"both":[206],"academic":[207],"research":[208],"creative":[210],"industries.":[211],"Code":[212],"available":[214],"https://github.com/liyiming09/RMD.":[216]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-06-13T00:00:00"}