{"id":"https://openalex.org/W4415031519","doi":"https://doi.org/10.1109/iccv51701.2025.01785","title":"SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing","display_name":"SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415031519","doi":"https://doi.org/10.1109/iccv51701.2025.01785"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.02370","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101476851","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-2671-5886"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057558573","display_name":"Xin Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xin Gu","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100578796","display_name":"Fan Chen","orcid":"https://orcid.org/0000-0002-4921-7484"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fan Chen","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028529893","display_name":"Xiaoying Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaoying Xing","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018942445","display_name":"Longyin Wen","orcid":"https://orcid.org/0000-0001-5525-492X"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Longyin Wen","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317030","display_name":"Chen Chen","orcid":"https://orcid.org/0009-0001-2214-3323"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Center for Research in Computer Vision, University of Central Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100627716","display_name":"Sijie Zhu","orcid":"https://orcid.org/0000-0002-0827-3156"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sijie Zhu","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19206","last_page":"19215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12500","display_name":"Reflective Practices in Education","score":0.882099986076355,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12500","display_name":"Reflective Practices in Education","score":0.882099986076355,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.885699987411499},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5949000120162964},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5871000289916992},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5479999780654907},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5457000136375427},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.5361999869346619}],"concepts":[{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.885699987411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8626999855041504},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5949000120162964},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5871000289916992},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5457000136375427},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.5361999869346619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5085999965667725},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3718000054359436},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33219999074935913},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C87829876","wikidata":"https://www.wikidata.org/wiki/Q648877","display_name":"Post-production","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C161615301","wikidata":"https://www.wikidata.org/wiki/Q309396","display_name":"Keystroke logging","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2676999866962433},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.02370","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.02370","pdf_url":"https://arxiv.org/pdf/2505.02370","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2505.02370","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.02370","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.02370","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.02370","pdf_url":"https://arxiv.org/pdf/2505.02370","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415031519.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Due":[0],"to":[1,20,38,58,87,100,135,205],"the":[2,26,84,91,121,172,188,244],"challenges":[3],"of":[4,120],"manually":[5],"collecting":[6],"accurate":[7],"editing":[8,29,40,75,85,98,109,137,144],"data,":[9],"existing":[10,232],"datasets":[11],"are":[12,141],"typically":[13],"constructed":[14],"using":[15,96,175],"various":[16],"automated":[17],"methods,":[18],"leading":[19],"noisy":[21],"supervision":[22,161,181,208],"signals":[23,162],"caused":[24],"by":[25,71],"mismatch":[27],"between":[28],"instructions":[30,76,86,99,167],"and":[31,95,165,168,202,210,215,252],"original-edited":[32,92],"image":[33,79,93,220],"pairs.":[34,80],"Recent":[35],"efforts":[36],"attempt":[37],"improve":[39],"models":[41,54,110],"through":[42],"generating":[43],"higher-quality":[44],"edited":[45],"images,":[46],"pre-training":[47,192],"on":[48,124,223,243],"recognition":[49],"tasks,":[50],"or":[51,191],"introducing":[52],"vision-language":[53],"(VLMs)":[55],"but":[56],"fail":[57],"resolve":[59],"this":[60,64,155],"fundamental":[61],"issue.":[62],"In":[63],"paper,":[65],"we":[66,106,128,157,239],"offer":[67],"a":[68,130,199,212],"novel":[69],"solution":[70,217],"constructing":[72],"more":[73,200],"effective":[74,216],"for":[77,133,218],"given":[78],"This":[81],"includes":[82],"rectifying":[83],"better":[88,207],"align":[89],"with":[90,151,163,235,247],"pairs":[94],"contrastive":[97,160],"further":[101,158,179],"enhance":[102],"their":[103],"effectiveness.":[104,182],"Specifically,":[105],"find":[107],"that":[108,146,227],"exhibit":[111],"specific":[112],"generation":[113],"attributes":[114],"at":[115],"different":[116],"inference":[117],"steps,":[118],"independent":[119],"text.":[122],"Based":[123],"these":[125],"prior":[126],"attributes,":[127],"define":[129],"unified":[131],"guide":[132],"VLMs":[134],"rectify":[136],"instructions.":[138,153],"However,":[139],"there":[140],"some":[142],"challenging":[143],"scenarios":[145],"cannot":[147],"be":[148],"resolved":[149],"solely":[150],"rectified":[152],"To":[154],"end,":[156],"construct":[159],"positive":[164],"negative":[166],"introduce":[169],"them":[170],"into":[171],"model":[173,255],"training":[174,250],"triplet":[176],"loss,":[177],"thereby":[178],"facilitating":[180],"Our":[183],"method":[184,229],"does":[185],"not":[186],"require":[187],"VLM":[189],"modules":[190],"tasks":[193],"used":[194],"in":[195],"previous":[196,236],"work,":[197],"offering":[198],"direct":[201],"efficient":[203],"way":[204],"provide":[206],"signals,":[209],"providing":[211],"novel,":[213],"simple,":[214],"instruction-based":[219],"editing.":[221],"Results":[222],"multiple":[224],"benchmarks":[225],"demonstrate":[226],"our":[228],"significantly":[230],"outperforms":[231],"approaches.":[233],"Compared":[234],"SOTA":[237],"SmartEdit,":[238],"achieve":[240],"9.19%":[241],"improvements":[242],"Real-Edit":[245],"benchmark":[246],"30x":[248],"less":[249],"data":[251],"13x":[253],"smaller":[254],"size.":[256]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}