{"id":"https://openalex.org/W4404527328","doi":"https://doi.org/10.1145/3687957","title":"SGEdit: Bridging LLM with Text2Image Generative Model for Scene Graph-based Image Editing","display_name":"SGEdit: Bridging LLM with Text2Image Generative Model for Scene Graph-based Image Editing","publication_year":2024,"publication_date":"2024-11-19","ids":{"openalex":"https://openalex.org/W4404527328","doi":"https://doi.org/10.1145/3687957"},"language":"en","primary_location":{"id":"doi:10.1145/3687957","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3687957","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-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":"https://openalex.org/A5100403362","display_name":"Zhiyuan Zhang","orcid":"https://orcid.org/0009-0002-4619-5117"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhang","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0002-4619-5117","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364587","display_name":"Dongdong Chen","orcid":"https://orcid.org/0000-0002-4642-4373"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DongDong Chen","raw_affiliation_strings":["Microsoft GenAI, Redmond, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-4642-4373","affiliations":[{"raw_affiliation_string":"Microsoft GenAI, Redmond, United States of America","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013972536","display_name":"Jing Liao","orcid":"https://orcid.org/0000-0001-7014-5377"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Liao","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7014-5377","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9831,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75248281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"43","issue":"6","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9954000115394592,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9954000115394592,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9945999979972839,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9943000078201294,"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/bridging","display_name":"Bridging (networking)","score":0.7969346046447754},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7129881978034973},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.6884095072746277},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6371240615844727},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6262420415878296},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5134618878364563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5028026103973389},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4683111608028412},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45018211007118225},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43886107206344604},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4069846570491791},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.3686010241508484},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2080461084842682}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7969346046447754},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7129881978034973},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.6884095072746277},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6371240615844727},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6262420415878296},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5134618878364563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5028026103973389},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4683111608028412},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45018211007118225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43886107206344604},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4069846570491791},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.3686010241508484},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2080461084842682},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3687957","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3687957","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2077069816","https://openalex.org/W2133665775","https://openalex.org/W2277195237","https://openalex.org/W2560662850","https://openalex.org/W2962785568","https://openalex.org/W2963184176","https://openalex.org/W3016121695","https://openalex.org/W3159481202","https://openalex.org/W3202536355","https://openalex.org/W3205398323","https://openalex.org/W4312933868","https://openalex.org/W4313026212","https://openalex.org/W4379261331","https://openalex.org/W4385271281","https://openalex.org/W4385815563","https://openalex.org/W4386057725","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4386083141","https://openalex.org/W4386113271","https://openalex.org/W4388187930","https://openalex.org/W4389539271","https://openalex.org/W4390190127","https://openalex.org/W4390872671","https://openalex.org/W4393148852","https://openalex.org/W4402733577","https://openalex.org/W4402753507","https://openalex.org/W6600005967"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W2186557420","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Scene":[0],"graphs":[1],"offer":[2],"a":[3,24,40,85,119,140],"structured,":[4],"hierarchical":[5],"representation":[6],"of":[7,70,188],"images,":[8],"with":[9,49,118,126],"nodes":[10],"and":[11,15,33,67,98,111,130,170,191],"edges":[12],"symbolizing":[13],"objects":[14,97],"the":[16,64,136,145,161],"relationships":[17],"among":[18],"them.":[19],"It":[20],"can":[21],"serve":[22],"as":[23,101,103,108],"natural":[25],"interface":[26],"for":[27,53],"image":[28,56,75,137,183],"editing,":[29],"dramatically":[30],"improving":[31],"precision":[32,190],"flexibility.":[34],"Leveraging":[35],"this":[36],"benefit,":[37],"we":[38,89,175],"introduce":[39],"new":[41],"framework":[42,179],"that":[43,177],"integrates":[44],"large":[45],"language":[46],"model":[47,52,163],"(LLM)":[48],"Text2Image":[50],"generative":[51],"scene":[54,87,93,192],"graph-based":[55],"editing.":[57],"This":[58],"integration":[59],"enables":[60],"precise":[61],"modifications":[62],"at":[63,198],"object":[65,109,125,166],"level":[66],"creative":[68],"recomposition":[69],"scenes":[71],"without":[72],"compromising":[73],"overall":[74],"integrity.":[76],"Our":[77,194],"approach":[78],"involves":[79],"two":[80],"primary":[81],"stages:":[82],"1)":[83],"Utilizing":[84],"LLM-driven":[86],"parser,":[88],"construct":[90],"an":[91,127,156],"image's":[92],"graph,":[94],"capturing":[95],"key":[96],"their":[99],"interrelationships,":[100],"well":[102],"parsing":[104],"fine-grained":[105],"attributes":[106],"such":[107],"masks":[110],"descriptions.":[112],"These":[113,150],"annotations":[114],"facilitate":[115],"concept":[116],"learning":[117],"fine-tuned":[120,162],"diffusion":[121,158],"model,":[122],"representing":[123],"each":[124],"optimized":[128],"token":[129],"detailed":[131],"description":[132],"prompt.":[133],"2)":[134],"During":[135],"editing":[138,142,184,189],"phase,":[139],"LLM":[141],"controller":[143],"guides":[144],"edits":[146,151],"towards":[147],"specific":[148],"areas.":[149],"are":[152],"then":[153],"implemented":[154],"by":[155],"attention-modulated":[157],"editor,":[159],"utilizing":[160],"to":[164],"perform":[165],"additions,":[167],"deletions,":[168],"replacements,":[169],"adjustments.":[171],"Through":[172],"extensive":[173],"experiments,":[174],"demonstrate":[176],"our":[178],"significantly":[180],"outperforms":[181],"existing":[182],"methods":[185],"in":[186],"terms":[187],"aesthetics.":[193],"code":[195],"is":[196],"available":[197],"https://bestzzhang.github.io/SGEdit.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}