{"id":"https://openalex.org/W4412673702","doi":"https://doi.org/10.1145/3730926","title":"MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills","display_name":"MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills","publication_year":2025,"publication_date":"2025-07-27","ids":{"openalex":"https://openalex.org/W4412673702","doi":"https://doi.org/10.1145/3730926"},"language":"en","primary_location":{"id":"doi:10.1145/3730926","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730926","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3730926","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077635429","display_name":"Niladri Shekhar Dutt","orcid":"https://orcid.org/0000-0002-7423-2221"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Niladri Shekhar Dutt","raw_affiliation_strings":["University College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-7423-2221","affiliations":[{"raw_affiliation_string":"University College London, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103140747","display_name":"Duygu Ceylan","orcid":"https://orcid.org/0000-0002-2307-9052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duygu Ceylan","raw_affiliation_strings":["Adobe Research, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-2307-9052","affiliations":[{"raw_affiliation_string":"Adobe Research, London, United Kingdom","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058170430","display_name":"Niloy J. Mitra","orcid":"https://orcid.org/0000-0002-2597-0914"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Niloy J. Mitra","raw_affiliation_strings":["Adobe Research, London, United Kingdom","University College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-2597-0914","affiliations":[{"raw_affiliation_string":"Adobe Research, London, United Kingdom","institution_ids":[]},{"raw_affiliation_string":"University College London, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077635429"],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30637394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":"4","first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9959999918937683,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9959999918937683,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9954000115394592,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.994700014591217,"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/computer-graphics","display_name":"Computer graphics (images)","score":0.6000979542732239},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5969027280807495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5872088670730591},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4983072280883789},{"id":"https://openalex.org/keywords/image-manipulation","display_name":"Image manipulation","score":0.47037023305892944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42631274461746216}],"concepts":[{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.6000979542732239},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5969027280807495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5872088670730591},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4983072280883789},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.47037023305892944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42631274461746216}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3730926","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730926","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2505.06176","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.06176","pdf_url":"https://arxiv.org/pdf/2505.06176","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"doi:10.1145/3730926","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730926","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F7525545622","display_name":"Adobe Research","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1920280450","https://openalex.org/W2025328853","https://openalex.org/W2962785568","https://openalex.org/W2963452532","https://openalex.org/W2963466723","https://openalex.org/W2998723654","https://openalex.org/W3107259129","https://openalex.org/W3108379454","https://openalex.org/W3154933072","https://openalex.org/W3167762716","https://openalex.org/W3176674719","https://openalex.org/W4312933868","https://openalex.org/W4385801403","https://openalex.org/W4389821092","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4390873485","https://openalex.org/W4402667093","https://openalex.org/W4404356600","https://openalex.org/W4404672267","https://openalex.org/W4409190811","https://openalex.org/W6600031136"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Retouching":[0],"is":[1,73],"an":[2,140],"essential":[3],"task":[4],"in":[5,34,219],"post-manipulation":[6],"of":[7,30,110,124,156,213,221],"raw":[8,97],"photographs.":[9],"Generative":[10],"editing,":[11],"guided":[12],"by":[13,48,60,130,164,190,193],"text":[14],"or":[15],"strokes,":[16],"provides":[17],"a":[18,86,107,154,161,173,211],"new":[19],"tool":[20],"accessible":[21],"to":[22,75,95,133,180],"users":[23],"but":[24],"can":[25,92,119,143,202,239],"easily":[26],"change":[27],"the":[28,31,125,167,177,194],"identity":[29,224],"original":[32],"objects":[33],"unacceptable":[35],"and":[36,102,146,170,199,201,216,223,229,236],"unpredictable":[37],"ways.":[38],"In":[39,80],"contrast,":[40],"although":[41],"traditional":[42],"procedural":[43,69,112,231],"edits,":[44],"as":[45],"commonly":[46],"supported":[47],"photoediting":[49],"tools":[50],"(e.g.,":[51],"Gimp,":[52],"Lightroom),":[53],"are":[54,57],"conservative,":[55],"they":[56],"still":[58],"preferred":[59],"professionals.":[61],"Unfortunately,":[62],"professional":[63],"quality":[64],"retouching":[65,187],"involves":[66],"many":[67],"individual":[68],"editing":[70],"operations":[71,188],"that":[72,117],"challenging":[74],"plan":[76,145],"for":[77,183],"most":[78],"novices.":[79],"this":[81],"paper,":[82],"we":[83,159],"ask":[84],"if":[85],"multimodal":[87],"large":[88],"language":[89],"model":[90],"(MLLM)":[91],"be":[93,120,203,240],"taught":[94],"critique":[96],"photographs,":[98],"suggest":[99],"suitable":[100],"remedies,":[101],"finally":[103],"realize":[104],"them":[105,132],"with":[106],"given":[108,153],"set":[109,155],"pre-authored":[111],"image":[113,127],"operations.":[114],"We":[115,206],"demonstrate":[116],"MLLMs":[118],"first":[121],"made":[122],"aware":[123],"underlying":[126],"processing":[128],"operations,":[129],"training":[131],"solve":[134],"specially-designed":[135],"visual":[136,178],"puzzles.":[137],"Subsequently,":[138],"such":[139],"operation-aware":[141],"MLLM":[142],"both":[144],"propose":[147],"edit":[148],"sequences.":[149],"To":[150],"facilitate":[151],"training,":[152],"expert-edited":[157],"photos,":[158],"synthesize":[160,181],"reasoning":[162,182],"dataset":[163],"procedurally":[165],"manipulating":[166],"expert":[168],"edits":[169],"then":[171],"grounding":[172],"pretrained":[174],"LLM":[175],"on":[176,210],"adjustments,":[179],"finetuning.":[184],"The":[185],"proposed":[186],"are,":[189],"construction,":[191],"understandable":[192],"users,":[195],"preserve":[196],"object":[197],"details":[198],"resolution,":[200],"optionally":[204],"overridden.":[205],"evaluate":[207],"our":[208,243],"setup":[209],"variety":[212],"test":[214],"examples":[215],"show":[217],"advantages,":[218],"terms":[220],"explainability":[222],"preservation,":[225],"over":[226],"existing":[227],"generative":[228],"other":[230],"alternatives.":[232],"Code,":[233],"data,":[234],"models,":[235],"supplementary":[237],"results":[238],"found":[241],"via":[242],"project":[244],"website":[245],"at":[246],"https://monetgpt.github.io.":[247]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}