{"id":"https://openalex.org/W4417183006","doi":"https://doi.org/10.1109/iccv51701.2025.01479","title":"ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation","display_name":"ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417183006","doi":"https://doi.org/10.1109/iccv51701.2025.01479"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01479","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/2507.01496","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037195485","display_name":"Jimyeong Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jimyeong Kim","raw_affiliation_strings":["Department of Intelligence and Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence and Information","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100650928","display_name":"Jungwon Park","orcid":"https://orcid.org/0000-0003-2927-4331"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jungwon Park","raw_affiliation_strings":["Department of Intelligence and Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence and Information","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103100996","display_name":"Yeji Song","orcid":"https://orcid.org/0000-0002-5436-5801"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeji Song","raw_affiliation_strings":["Department of Intelligence and Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence and Information","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084897975","display_name":"Nojun Kwak","orcid":"https://orcid.org/0000-0002-1792-0327"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nojun Kwak","raw_affiliation_strings":["Department of Intelligence and Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence and Information","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056032525","display_name":"Wonjong Rhee","orcid":"https://orcid.org/0000-0002-2590-8774"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wonjong Rhee","raw_affiliation_strings":["Department of Intelligence and Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence and Information","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"15939","last_page":"15948"},"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":0.8533999919891357,"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":0.8533999919891357,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.019200000911951065,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.01640000008046627,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6571000218391418},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5497999787330627},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5077999830245972},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.4187000095844269},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.40939998626708984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37049999833106995},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.36570000648498535},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.36570000648498535}],"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/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6894999742507935},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6571000218391418},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5884000062942505},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5497999787330627},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5077999830245972},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.4187000095844269},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.40939998626708984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.36570000648498535},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C2985179714","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Work flow","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.31220000982284546},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01479","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:2507.01496","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01496","pdf_url":"https://arxiv.org/pdf/2507.01496","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2507.01496","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.01496","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.01496","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01496","pdf_url":"https://arxiv.org/pdf/2507.01496","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://openalex.org/G2583072699","display_name":null,"funder_award_id":"RS-2021-II211343","funder_id":"https://openalex.org/F4320319144","funder_display_name":"Indian Institute of Technology, Patna"},{"id":"https://openalex.org/G7580349198","display_name":null,"funder_award_id":"RS-2023-00235293","funder_id":"https://openalex.org/F4320321292","funder_display_name":"Seoul National University"}],"funders":[{"id":"https://openalex.org/F4320319144","display_name":"Indian Institute of Technology, Patna","ror":"https://ror.org/01ft5vz71"},{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Rectified":[0],"Flow":[1],"text-to-image":[2],"models":[3,6],"surpass":[4],"diffusion":[5],"in":[7],"image":[8],"quality":[9],"and":[10,39,76,91],"text":[11],"alignment,":[12],"but":[13],"adapting":[14],"ReFlow":[15,29],"for":[16,28,125],"real-image":[17,25],"editing":[18,26],"remains":[19],"challenging.":[20],"We":[21,67],"propose":[22],"a":[23,97,121],"new":[24],"method":[27,84],"by":[30,117],"analyzing":[31],"the":[32,65,80],"intermediate":[33],"representations":[34],"of":[35],"multimodal":[36],"transformer":[37],"blocks":[38],"identifying":[40],"three":[41],"key":[42],"features.":[43],"To":[44],"extract":[45],"these":[46],"features":[47],"from":[48],"real":[49],"images":[50],"with":[51,105],"sufficient":[52],"structural":[53],"preservation,":[54],"we":[55],"leverage":[56],"mid-step":[57],"latent,":[58],"which":[59],"is":[60,85],"inverted":[61],"only":[62],"up":[63],"to":[64,73,79],"mid-step.":[66],"then":[68],"adapt":[69],"attention":[70],"during":[71],"injection":[72],"improve":[74],"editability":[75],"enhance":[77],"alignment":[78],"target":[81],"text.":[82],"Our":[83],"training-free,":[86],"requires":[87],"no":[88],"user-provided":[89],"mask,":[90],"can":[92],"be":[93],"applied":[94],"even":[95],"without":[96],"source":[98],"prompt.":[99],"Extensive":[100],"experiments":[101],"on":[102],"two":[103],"benchmarks":[104],"nine":[106],"baselines":[107],"demonstrate":[108],"its":[109],"superior":[110],"performance":[111],"over":[112],"prior":[113],"methods,":[114],"further":[115],"validated":[116],"human":[118],"evaluations":[119],"confirming":[120],"strong":[122],"user":[123],"preference":[124],"our":[126],"approach.":[127]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}