{"id":"https://openalex.org/W4415626503","doi":"https://doi.org/10.1109/tip.2025.3623869","title":"Consistent Image Layout Editing With Diffusion Models","display_name":"Consistent Image Layout Editing With Diffusion Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415626503","doi":"https://doi.org/10.1109/tip.2025.3623869","pmid":"https://pubmed.ncbi.nlm.nih.gov/41150226"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3623869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3623869","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":null,"display_name":"Tao Xia","orcid":"https://orcid.org/0009-0001-5485-7160"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Xia","raw_affiliation_strings":["School of Computer, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-5485-7160","affiliations":[{"raw_affiliation_string":"School of Computer, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yudi Zhang","orcid":"https://orcid.org/0009-0004-5581-0235"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudi Zhang","raw_affiliation_strings":["School of Computer, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-5581-0235","affiliations":[{"raw_affiliation_string":"School of Computer, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418161","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0003-0749-064X"},"institutions":[{"id":"https://openalex.org/I4210140416","display_name":"New England Biolabs (China)","ror":"https://ror.org/03nb3ch98","country_code":"CN","type":"company","lineage":["https://openalex.org/I115020962","https://openalex.org/I4210140416"]},{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["MT Laboratory, Meitu Inc., Beijing, China","MTLab, Meitu Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MT Laboratory, Meitu Inc., Beijing, China","institution_ids":["https://openalex.org/I4210152823"]},{"raw_affiliation_string":"MTLab, Meitu Inc, Beijing, China","institution_ids":["https://openalex.org/I4210140416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101484030","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-2286-0314"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["School of Computer, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2286-0314","affiliations":[{"raw_affiliation_string":"School of Computer, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27501346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"6978","last_page":"6992"},"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":0.8666999936103821,"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":0.8666999936103821,"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":0.01269999984651804,"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"}},{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.007499999832361937,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6173999905586243},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5777999758720398},{"id":"https://openalex.org/keywords/anisotropic-diffusion","display_name":"Anisotropic diffusion","score":0.4772999882698059},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4609000086784363},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.4300000071525574},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.41519999504089355},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.40939998626708984},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.362199991941452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804099977016449},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6173999905586243},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5777999758720398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.569599986076355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5601000189781189},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.4772999882698059},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4300000071525574},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.41519999504089355},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.35670000314712524},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.34610000252723694},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3305000066757202},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3075999915599823},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C188985296","wikidata":"https://www.wikidata.org/wiki/Q868954","display_name":"Page layout","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.27720001339912415},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3623869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3623869","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:41150226","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41150226","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":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2369050462","display_name":null,"funder_award_id":"2022YFC3303600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6578933956","display_name":null,"funder_award_id":"ZR2024ZD12","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2294798173","https://openalex.org/W3143092915","https://openalex.org/W3159481202","https://openalex.org/W3166852674","https://openalex.org/W3176032345","https://openalex.org/W3176641147","https://openalex.org/W3199003182","https://openalex.org/W3216352822","https://openalex.org/W4312740349","https://openalex.org/W4312771828","https://openalex.org/W4312933868","https://openalex.org/W4385271281","https://openalex.org/W4385535331","https://openalex.org/W4386057725","https://openalex.org/W4386072096","https://openalex.org/W4386075890","https://openalex.org/W4386076027","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4388416520","https://openalex.org/W4388519998","https://openalex.org/W4390872387","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4390873211","https://openalex.org/W4390874575","https://openalex.org/W4393148753","https://openalex.org/W4394625750","https://openalex.org/W4402716297","https://openalex.org/W4402727040","https://openalex.org/W4402727074","https://openalex.org/W4403770038","https://openalex.org/W4408016691","https://openalex.org/W7103748293"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,21,42,51,87,91,111,137,148,154,159,175,182,205,219],"great":[2],"success":[3,178],"of":[4,23,54,90,113,143,151,161,180,186,221],"large-scale":[5],"text-to-image":[6],"diffusion":[7,144],"models":[8,145],"in":[9,49,211],"image":[10,13,43,68,78,131,222],"generation":[11],"and":[12,177,192,215],"editing,":[14],"existing":[15,209],"methods":[16,210],"still":[17],"struggle":[18],"with":[19,95],"editing":[20,70,198],"layout":[22,44,57,69,132,213,223],"real-world":[24,77],"images.":[25],"Although":[26],"a":[27,66,76,80,103,117,125,166,195],"few":[28],"works":[29],"have":[30],"been":[31],"developed":[32,108],"to":[33,40,79,100,109,146,153,157,173],"address":[34],"this":[35,61,63],"issue,":[36],"they":[37],"either":[38],"fail":[39],"adjust":[41],"effectively":[45],"or":[46],"encounter":[47],"challenges":[48],"preserving":[50],"visual":[52,88,216],"appearance":[53,89,149],"objects":[55,92,115,152,162],"after":[56,163],"adjustment.":[58],"To":[59],"bridge":[60],"gap,":[62],"paper":[64],"proposes":[65],"novel":[67,126,167,196],"method":[71,207],"that":[72,86,204],"not":[73],"only":[74],"re-arranges":[75],"specified":[81],"layout,":[82],"but":[83],"also":[84,190],"ensures":[85],"remains":[93],"consistent":[94],"their":[96],"original":[97],"state":[98],"prior":[99],"editing.":[101,133,164,224],"Concretely,":[102],"Multi-Concept":[104],"Learning":[105],"scheme":[106,128],"is":[107,171,189],"learn":[110],"concepts":[112],"different":[114],"from":[116],"single":[118],"image,":[119],"which":[120],"can":[121],"be":[122],"seen":[123],"as":[124],"inversion":[127],"tailored":[129],"for":[130,218],"Then,":[134],"we":[135],"leverage":[136],"semantic":[138],"consistency":[139,217],"within":[140],"intermediate":[141],"features":[142],"project":[147],"information":[150],"target":[155],"regions":[156],"improve":[158],"fidelity":[160],"Additionally,":[165],"initialization":[168],"noise":[169],"design":[170],"adopted":[172],"facilitate":[174],"convergence":[176],"rate":[179],"re-arranging":[181],"layout.":[183],"The":[184],"phenomenon":[185],"concept":[187],"entanglement":[188],"analyzed,":[191],"resolved":[193],"by":[194],"asynchronous":[197],"strategy.":[199],"Extensive":[200],"experimental":[201],"results":[202],"demonstrate":[203],"proposed":[206],"outperforms":[208],"both":[212],"alignment":[214],"task":[220]},"counts_by_year":[],"updated_date":"2025-11-06T23:17:08.748858","created_date":"2025-10-29T00:00:00"}