{"id":"https://openalex.org/W4415540372","doi":"https://doi.org/10.1145/3746027.3755294","title":"LMM4Edit: Benchmarking and Evaluating Multimodal Image Editing with LMMs","display_name":"LMM4Edit: Benchmarking and Evaluating Multimodal Image Editing with LMMs","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540372","doi":"https://doi.org/10.1145/3746027.3755294"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755294","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113024597","display_name":"Zitong Xu","orcid":null},"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":"Zitong Xu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-7834-6179","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015291775","display_name":"Huiyu Duan","orcid":"https://orcid.org/0000-0002-6519-4067"},"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":"Huiyu Duan","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6519-4067","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bingnan Liu","orcid":"https://orcid.org/0009-0002-9627-9562"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingnan Liu","raw_affiliation_strings":["UESTC, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0002-9627-9562","affiliations":[{"raw_affiliation_string":"UESTC, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109878866","display_name":"G. Ma","orcid":null},"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":"Guangji Ma","raw_affiliation_strings":["Shanghai Jiao Tong University, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0001-8136-1187","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Chengdu, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115594995","display_name":"Jiarui Wang","orcid":"https://orcid.org/0009-0005-9890-2698"},"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":"Jiarui Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-9890-2698","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101945669","display_name":"Yang Liu","orcid":"https://orcid.org/0009-0004-1300-7401"},"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":"Liu Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-1300-7401","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shiqi Gao","orcid":"https://orcid.org/0009-0003-2428-0326"},"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":"Shiqi Gao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-2428-0326","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoyu Wang","orcid":"https://orcid.org/0009-0001-3415-6201"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Wang","raw_affiliation_strings":["UESTC, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0001-3415-6201","affiliations":[{"raw_affiliation_string":"UESTC, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404634","display_name":"Jia Wang","orcid":"https://orcid.org/0000-0002-1714-3206"},"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":"Jia Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1714-3206","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043405654","display_name":"Xiongkuo Min","orcid":"https://orcid.org/0000-0001-5693-0416"},"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":"Xiongkuo Min","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5693-0416","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"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":"Guangtao Zhai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8165-9322","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403129","display_name":"Weisi Lin","orcid":"https://orcid.org/0000-0001-9866-1947"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weisi Lin","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9866-1947","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6908","last_page":"6917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9944999814033508,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9944999814033508,"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":0.9890999794006348,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9775000214576721,"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/benchmarking","display_name":"Benchmarking","score":0.7174999713897705},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6638000011444092},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6517000198364258},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6036999821662903},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5740000009536743},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5709999799728394},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.527400016784668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670999765396118},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7174999713897705},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6638000011444092},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6517000198364258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6308000087738037},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5740000009536743},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5709999799728394},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.527400016784668},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5062999725341797},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.34470000863075256},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3068999946117401},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2994999885559082},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2930999994277954},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.29109999537467957},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25099998712539673},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755294","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4507737079","display_name":null,"funder_award_id":"BX20250411, 2025M773473","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1964859077","https://openalex.org/W2046119925","https://openalex.org/W2051596736","https://openalex.org/W2102166818","https://openalex.org/W2129644086","https://openalex.org/W2133665775","https://openalex.org/W2141983208","https://openalex.org/W2142884912","https://openalex.org/W2162692770","https://openalex.org/W2509784253","https://openalex.org/W2560533888","https://openalex.org/W2563786098","https://openalex.org/W2754213847","https://openalex.org/W2799192307","https://openalex.org/W2905544033","https://openalex.org/W2963014378","https://openalex.org/W2966858528","https://openalex.org/W3035719652","https://openalex.org/W3096831136","https://openalex.org/W3201952986","https://openalex.org/W4221144351","https://openalex.org/W4224267514","https://openalex.org/W4224852017","https://openalex.org/W4312872987","https://openalex.org/W4312933868","https://openalex.org/W4312968447","https://openalex.org/W4382462760","https://openalex.org/W4386057725","https://openalex.org/W4386076215","https://openalex.org/W4390873195","https://openalex.org/W4390874314","https://openalex.org/W4393078930","https://openalex.org/W4396818947","https://openalex.org/W4402753379","https://openalex.org/W4402753812","https://openalex.org/W4402753860","https://openalex.org/W4402753991","https://openalex.org/W4402916399","https://openalex.org/W4413147296","https://openalex.org/W4413158015"],"related_works":[],"abstract_inverted_index":{"The":[0,198],"rapid":[1],"advancement":[2],"of":[3,195],"Text-guided":[4],"Image":[5],"Editing":[6,61,153],"(TIE)":[7],"enables":[8],"image":[9,22,60,152],"modifications":[10],"through":[11],"text":[12],"prompts.":[13],"However,":[14],"current":[15],"TIE":[16,37,95],"models":[17,154],"still":[18],"struggle":[19],"to":[20,119],"balance":[21],"quality,":[23,157],"editing":[24,83,158],"alignment,":[25,159],"and":[26,40,107,140,162,178,200],"consistency":[27],"with":[28,48,67,81,181],"the":[29,57,124,133,136,187,192],"original":[30],"image,":[31],"limiting":[32],"their":[33],"practical":[34],"applications.":[35],"Existing":[36],"evaluation":[38,105,125],"benchmarks":[39],"metrics":[41],"have":[42],"limitations":[43],"on":[44,113,186],"scale":[45],"or":[46],"alignment":[47,134],"human":[49,69,141,182],"perception.":[50],"To":[51],"this":[52],"end,":[53],"we":[54,115,144],"introduce":[55],"EBench-18K,":[56,114],"first":[58],"large-scale":[59],"Benchmark":[62],"including":[63],"18K":[64],"edited":[65,89,121],"images":[66,80,90],"fine-grained":[68],"preference":[70],"annotations":[71],"for":[72,150],"evaluating":[73,151],"TIE.":[74],"Specifically,":[75],"EBench-18K":[76],"includes":[77],"1,080":[78],"source":[79],"corresponding":[82],"prompts":[84],"across":[85],"21":[86],"tasks,":[87],"18K+":[88,108],"produced":[91],"by":[92],"17":[93],"state-of-the-art":[94],"models,":[96],"55K+":[97],"mean":[98],"opinion":[99],"scores":[100],"(MOSs)":[101],"assessed":[102],"from":[103,155],"three":[104],"dimensions,":[106],"question-answering":[109],"(QA)":[110],"pairs.":[111],"Based":[112],"employ":[116],"outstanding":[117,176],"LMMs":[118],"assess":[120],"images,":[122],"while":[123],"results,":[126],"in":[127,166],"turn,":[128],"provide":[129],"insights":[130],"into":[131],"assessing":[132],"between":[135],"LMMs'":[137],"understanding":[138],"ability":[139,194],"preferences.":[142],"Then,":[143],"propose":[145],"LMM4Edit,":[146],"a":[147],"LMM-based":[148],"metric":[149],"perceptual":[156],"attribute":[160],"preservation,":[161],"task-specific":[163],"QA":[164],"accuracy":[165],"an":[167],"all-in-one":[168],"manner.":[169],"Extensive":[170],"experiments":[171],"show":[172],"that":[173],"LMM4Edit":[174],"achieves":[175],"performance":[177],"aligns":[179],"well":[180],"preference.":[183],"Zero-shot":[184],"validation":[185],"other":[188],"datasets":[189],"also":[190],"shows":[191],"generalization":[193],"our":[196],"model.":[197],"dataset":[199],"code":[201],"are":[202],"available":[203],"at":[204],"https://github.com/IntMeGroup/LMM4Edit.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}