{"id":"https://openalex.org/W7109979670","doi":"https://doi.org/10.1145/3757377.3763909","title":"ConsistEdit: Highly Consistent and Precise Training-free Visual Editing","display_name":"ConsistEdit: Highly Consistent and Precise Training-free Visual Editing","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7109979670","doi":"https://doi.org/10.1145/3757377.3763909"},"language":"en","primary_location":{"id":"doi:10.1145/3757377.3763909","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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":"Zixin Yin","orcid":"https://orcid.org/0000-0003-0443-7915"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zixin Yin","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ling-Hao Chen","orcid":"https://orcid.org/0000-0002-2528-6178"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling-Hao Chen","raw_affiliation_strings":["Tsinghua University, Shenzhen, China and International Digital Economy Academy, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China and International Digital Economy Academy, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lionel Ni","orcid":"https://orcid.org/0000-0002-2325-6215"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lionel Ni","raw_affiliation_strings":["Hong Kong University of Science and Technology, Guangzhou, Guangzhou, China and Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Guangzhou, Guangzhou, China and Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xili Dai","orcid":"https://orcid.org/0000-0001-5526-8934"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xili Dai","raw_affiliation_strings":["Hong Kong University of Science and Technology, Guangzhou, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Guangzhou, Guangzhou, China","institution_ids":["https://openalex.org/I90610280","https://openalex.org/I37987034"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":1.304,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86975451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.21539999544620514,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.21539999544620514,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.13349999487400055,"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/T14114","display_name":"Digital Media and Philosophy","score":0.08240000158548355,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/image-editing","display_name":"Image editing","score":0.7450000047683716},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5478000044822693},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4778999984264374},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4000999927520752},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38929998874664307},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3384999930858612},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3098999857902527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803600013256073},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.7450000047683716},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4778999984264374},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34940001368522644},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3384999930858612},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.25690001249313354},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3757377.3763909","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-169932","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-169932","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5121017694473267,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2145023731","https://openalex.org/W2962770929","https://openalex.org/W4312234230","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W4386066404","https://openalex.org/W4386113271","https://openalex.org/W4390871782","https://openalex.org/W4390872297","https://openalex.org/W4390873195","https://openalex.org/W4390874567","https://openalex.org/W4394625750","https://openalex.org/W4402727429","https://openalex.org/W4402753991","https://openalex.org/W4402775818","https://openalex.org/W4413145411","https://openalex.org/W4413157726"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,40,49,62,114,267],"training-free":[3],"attention":[4,155,165,175,235],"control":[5,166],"methods":[6,77,138],"have":[7],"enabled":[8],"flexible":[9],"and":[10,18,64,117,125,180,187,209,216,234,242,248,271],"efficient":[11],"text-guided":[12],"editing":[13,30,211,229,270,275],"capabilities":[14],"for":[15,122,133,170],"existing":[16,76],"image":[17,208],"video":[19,65,210],"generation":[20],"models.":[21],"However,":[22],"current":[23],"approaches":[24],"struggle":[25,44],"to":[26,45,85,105,140,190,227],"simultaneously":[27],"deliver":[28],"strong":[29],"strength":[31],"while":[32,52,92],"preserving":[33,53,93],"consistency":[34,48],"with":[35],"the":[36,54,100,131,184,224,273],"source.":[37],"For":[38],"instance,":[39],"color-editing":[41],"tasks,":[42,212],"they":[43],"maintain":[46],"structural":[47,257],"edited":[50],"regions":[51],"rest":[55],"intact.":[56],"This":[57],"limitation":[58],"becomes":[59],"particularly":[60],"critical":[61],"multi-round":[63,247],"editing,":[66],"where":[67],"visual":[68],"errors":[69],"can":[70],"accumulate":[71],"over":[72],"time.":[73],"Moreover,":[74],"most":[75],"enforce":[78],"global":[79],"consistency,":[80,243,258],"which":[81,244],"limits":[82],"their":[83],"ability":[84],"modify":[86],"individual":[87],"attributes":[88],"such":[89],"as":[90],"texture":[91],"others,":[94],"thereby":[95],"hindering":[96],"fine-grained":[97],"editing.":[98,250],"Recently,":[99],"architectural":[101],"shift":[102],"from":[103],"U-Net":[104],"Multi-Modal":[106],"Diffusion":[107],"Transformers":[108],"(MM-DiT)":[109],"has":[110],"brought":[111],"significant":[112,265],"improvements":[113],"generative":[115,268],"performance":[116,202],"introduced":[118],"a":[119,163,204,264],"novel":[120,164],"mechanism":[121],"integrating":[123],"text":[124],"vision":[126],"modalities.":[127],"These":[128],"advancements":[129],"pave":[130],"way":[132],"overcoming":[134],"challenges":[135],"that":[136,198],"previous":[137],"failed":[139],"resolve.":[141],"Through":[142],"an":[143],"in-depth":[144],"analysis":[145],"of":[146,183,207,256,277],"MM-DiT,":[147],"we":[148,160],"identify":[149],"three":[150],"key":[151],"insights":[152],"into":[153],"its":[154],"mechanisms.":[156],"Building":[157],"on":[158],"these,":[159],"propose":[161],"ConsistEdit,":[162],"method":[167],"specifically":[168],"tailored":[169],"MM-DiT.":[171],"ConsistEdit":[172,199,262],"incorporates":[173],"vision-only":[174],"control,":[176],"mask-guided":[177],"pre-attention":[178],"fusion,":[179],"differentiated":[181],"manipulation":[182],"query,":[185],"key,":[186],"value":[188],"tokens":[189],"produce":[191],"consistent,":[192],"prompt-aligned":[193],"edits.":[194],"Extensive":[195],"experiments":[196],"demonstrate":[197],"achieves":[200],"state-of-the-art":[201],"across":[203,230],"wide":[205],"range":[206],"including":[213],"both":[214],"structure-consistent":[215],"structure-inconsistent":[217],"scenarios.":[218],"Unlike":[219],"prior":[220],"methods,":[221],"it":[222,252],"is":[223],"first":[225],"approach":[226],"perform":[228],"all":[231],"inference":[232],"steps":[233],"layers":[236],"without":[237],"handcraft,":[238],"significantly":[239],"enhancing":[240],"reliability":[241],"enables":[245],"robust":[246],"multi-region":[249],"Furthermore,":[251],"supports":[253],"progressive":[254],"adjustment":[255],"enabling":[259],"finer":[260],"control.":[261],"represents":[263],"advancement":[266],"model":[269],"unlocks":[272],"full":[274],"potential":[276],"MM-DiT":[278],"architectures.":[279]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-12-08T00:00:00"}
