{"id":"https://openalex.org/W4414448618","doi":"https://doi.org/10.1109/iccv51701.2025.01783","title":"Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent","display_name":"Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414448618","doi":"https://doi.org/10.1109/iccv51701.2025.01783"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01783","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/2508.20505","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116335736","display_name":"En Ci","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"En Ci","raw_affiliation_strings":["Nanjing University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070466381","display_name":"Shanyan Guan","orcid":"https://orcid.org/0000-0003-0875-167X"},"institutions":[{"id":"https://openalex.org/I4210125111","display_name":"Vietnamese Voluntary Foundation","ror":"https://ror.org/032eyp751","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210125111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanyan Guan","raw_affiliation_strings":["vivo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo,China","institution_ids":["https://openalex.org/I4210125111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032461971","display_name":"Yanhao Ge","orcid":"https://orcid.org/0000-0002-5650-5118"},"institutions":[{"id":"https://openalex.org/I4210125111","display_name":"Vietnamese Voluntary Foundation","ror":"https://ror.org/032eyp751","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210125111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanhao Ge","raw_affiliation_strings":["vivo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo,China","institution_ids":["https://openalex.org/I4210125111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100758234","display_name":"Yilin Zhang","orcid":"https://orcid.org/0000-0002-4448-0005"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Zhang","raw_affiliation_strings":["Nanjing University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318383","display_name":"Wei Li","orcid":"https://orcid.org/0000-0003-1733-7956"},"institutions":[{"id":"https://openalex.org/I4210125111","display_name":"Vietnamese Voluntary Foundation","ror":"https://ror.org/032eyp751","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210125111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["vivo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo,China","institution_ids":["https://openalex.org/I4210125111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389535","display_name":"Zhenyu Zhang","orcid":"https://orcid.org/0000-0002-5936-6678"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhang","raw_affiliation_strings":["Nanjing University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503975","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0002-1963-712X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["Nanjing University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029021362","display_name":"Ying Tai","orcid":"https://orcid.org/0000-0002-4665-6852"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Tai","raw_affiliation_strings":["Nanjing University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,China","institution_ids":["https://openalex.org/I881766915"]}]}],"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":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9399999976158142,"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":0.9399999976158142,"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/image-editing","display_name":"Image editing","score":0.8274000287055969},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5978000164031982},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48010000586509705},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.45879998803138733},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4413999915122986},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43549999594688416},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4320000112056732},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4212000072002411}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8565000295639038},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.8274000287055969},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5978000164031982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5716000199317932},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4717999994754791},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.45879998803138733},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4212000072002411},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.359499990940094},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.35830000042915344},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01783","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:2508.20505","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.20505","pdf_url":"https://arxiv.org/pdf/2508.20505","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.2508.20505","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.20505","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":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:2508.20505","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.20505","pdf_url":"https://arxiv.org/pdf/2508.20505","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/G1507308270","display_name":null,"funder_award_id":"62406135","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321881","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,56,70,94,124],"progress":[2],"in":[3,106],"text-to-image":[4,52,101],"generation,":[5],"semantic":[6],"image":[7,48,72,91],"editing":[8,37,131],"remains":[9],"a":[10,35,74,80],"challenge.":[11],"Inversion-based":[12],"algorithms":[13],"unavoidably":[14],"introduce":[15,79],"reconstruction":[16],"errors,":[17],"while":[18],"instruction-based":[19],"models":[20,62],"mainly":[21],"suffer":[22],"from":[23],"limited":[24],"dataset":[25,108],"quality":[26],"and":[27,73,115,118,133],"scale.":[28],"To":[29],"address":[30],"these":[31],"problems,":[32],"we":[33,78],"propose":[34],"descriptive-prompt-based":[36],"framework,":[38],"named":[39],"DescriptiveEdit.":[40],"The":[41],"core":[42],"idea":[43],"is":[44,119],"to":[45,88,99],"re-frame":[46],"`instruction-based":[47],"editing'":[49],"as":[50,76],"`reference-image-based":[51],"generation',":[53],"which":[54,83],"preserves":[55],"generative":[57],"power":[58],"of":[59],"well-trained":[60],"Text-to-Image":[61],"without":[63],"architectural":[64],"modifications":[65],"or":[66],"inversion.":[67],"Specifically,":[68],"taking":[69],"reference":[71,90],"prompt":[75],"input,":[77],"Cross-Attentive":[81],"UNet,":[82],"newly":[84],"adds":[85],"attention":[86],"bridges":[87],"inject":[89],"features":[92],"into":[93],"prompt-to-edit-image":[95],"generation":[96],"process.":[97],"Owing":[98],"its":[100],"nature,":[102],"DescriptiveEdit":[103],"overcomes":[104],"limitations":[105],"instruction":[107],"quality,":[109],"integrates":[110],"seamlessly":[111],"with":[112],"ControlNet,":[113],"IP-Adapter,":[114],"other":[116],"extensions,":[117],"more":[120],"scalable.":[121],"Experiments":[122],"on":[123],"Emu":[125],"Edit":[126],"benchmark":[127],"show":[128],"it":[129],"improves":[130],"accuracy":[132],"consistency.":[134]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}