{"id":"https://openalex.org/W7137870520","doi":"https://doi.org/10.1609/aaai.v40i4.37264","title":"PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching","display_name":"PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137870520","doi":"https://doi.org/10.1609/aaai.v40i4.37264"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i4.37264","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37264","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i4.37264","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089206339","display_name":"Zewei Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zewei Chang","raw_affiliation_strings":["VCIP, CS, Nankai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730547","display_name":"Zheng-Peng Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Peng Duan","raw_affiliation_strings":["VCIP, CS, Nankai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049156680","display_name":"Jianxing Zhang","orcid":"https://orcid.org/0000-0003-4091-2189"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jianxing Zhang","raw_affiliation_strings":["Samsung R&D Institute China - Beijing (SRC-B)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China - Beijing (SRC-B)","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129741939","display_name":"Chun-Le Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun-Le Guo","raw_affiliation_strings":["VCIP, CS, Nankai University\nNKIARI, Shenzhen Futian"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University\nNKIARI, Shenzhen Futian","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129735223","display_name":"Siyu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Liu","raw_affiliation_strings":["VCIP, CS, Nankai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129650263","display_name":"Hyungju Chun","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungju Chun","raw_affiliation_strings":["The Department of Camera Innovation Group, Samsung Electronics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Department of Camera Innovation Group, Samsung Electronics","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129671757","display_name":"Hyunhee Park","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunhee Park","raw_affiliation_strings":["The Department of Camera Innovation Group, Samsung Electronics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Department of Camera Innovation Group, Samsung Electronics","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129643884","display_name":"Zikun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Zikun Liu","raw_affiliation_strings":["Samsung R&D Institute China - Beijing (SRC-B)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China - Beijing (SRC-B)","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129708426","display_name":"Chongyi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongyi Li","raw_affiliation_strings":["VCIP, CS, Nankai University\nNKIARI, Shenzhen Futian"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University\nNKIARI, Shenzhen Futian","institution_ids":["https://openalex.org/I205237279"]}]}],"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":"40","issue":"4","first_page":"2752","last_page":"2759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9627000093460083,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9627000093460083,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.025299999862909317,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.001500000013038516,"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","display_name":"Image (mathematics)","score":0.600600004196167},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5512999892234802},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.4560000002384186},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.428600013256073},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3873000144958496},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3797999918460846},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.36039999127388},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.3515999913215637},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.3465000092983246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7713000178337097},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.600600004196167},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5512999892234802},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4560000002384186},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4316999912261963},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41999998688697815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41370001435279846},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.36039999127388},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C201025465","wikidata":"https://www.wikidata.org/wiki/Q11248500","display_name":"User experience design","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3257000148296356},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C3019635856","wikidata":"https://www.wikidata.org/wiki/Q1619726","display_name":"Background image","level":3,"score":0.3068999946117401},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C202708506","wikidata":"https://www.wikidata.org/wiki/Q7449050","display_name":"Semantic compression","level":5,"score":0.2904999852180481},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i4.37264","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37264","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i4.37264","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37264","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"retouching":[1,29,38],"aims":[2],"to":[3,93],"enhance":[4],"visual":[5,86],"quality":[6],"while":[7,39],"aligning":[8],"with":[9,85,102,113],"users'":[10],"personalized":[11,133],"aesthetic":[12],"preferences.":[13,119],"To":[14,65,80],"address":[15],"the":[16,127],"challenge":[17],"of":[18,104,130],"balancing":[19],"controllability":[20],"and":[21,74,97,107,116,126],"subjectivity,":[22],"we":[23,70,88],"propose":[24],"a":[25,90],"unified":[26],"diffusion-based":[27],"image":[28,37,63,134],"framework":[30],"called":[31],"PerTouch.":[32],"Our":[33],"method":[34],"supports":[35],"semantic-level":[36],"maintaining":[40],"global":[41],"aesthetics.":[42],"Using":[43],"parameter":[44,75],"maps":[45],"containing":[46],"attribute":[47],"values":[48],"in":[49,132],"specific":[50],"semantic":[51,67,72],"regions":[52],"as":[53],"input,":[54],"PerTouch":[55,110,131],"constructs":[56],"an":[57],"explicit":[58],"parameter-to-image":[59],"mapping":[60],"for":[61],"fine-grained":[62],"retouching.":[64,135],"improve":[66],"boundary":[68],"perception,":[69],"introduce":[71],"replacement":[73],"perturbation":[76],"mechanisms":[77,103],"during":[78],"training.":[79],"connect":[81],"natural":[82],"language":[83],"instructions":[84],"control,":[87],"develop":[89],"VLM-driven":[91],"agent":[92],"handle":[94],"both":[95],"strong":[96],"weak":[98],"user":[99,114],"instructions.":[100],"Equipped":[101],"feedback-driven":[105],"rethinking":[106],"scene-aware":[108],"memory,":[109],"better":[111],"aligns":[112],"intent":[115],"captures":[117],"long-term":[118],"Extensive":[120],"experiments":[121],"demonstrate":[122],"each":[123],"component\u2019s":[124],"effectiveness":[125],"superior":[128],"performance":[129]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}