{"id":"https://openalex.org/W7163033474","doi":"https://doi.org/10.48550/arxiv.2605.31039","title":"GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration","display_name":"GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163033474","doi":"https://doi.org/10.48550/arxiv.2605.31039"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.31039","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31039","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.31039","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137575497","display_name":"Xiangtao Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Xiangtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102296952","display_name":"Jixin Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jixin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023365341","display_name":"Lingchen Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Lingchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061924580","display_name":"Rongyuan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Rongyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137584375","display_name":"Lei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":null,"last_page":null},"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":0.8683000206947327,"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":0.8683000206947327,"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":0.07109999656677246,"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/T11019","display_name":"Image Enhancement Techniques","score":0.034699998795986176,"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/generalization","display_name":"Generalization","score":0.7961999773979187},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7868000268936157},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.7156000137329102},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5687000155448914},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5536999702453613},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5375000238418579},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5306000113487244},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5134000182151794}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7961999773979187},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7868000268936157},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.7156000137329102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6728000044822693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.649399995803833},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5687000155448914},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5157999992370605},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5134000182151794},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.3366999924182892},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.26579999923706055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.31039","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31039","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":"doi:10.48550/arxiv.2605.31039","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31039","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.4182668626308441}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"image":[1,172],"restoration":[2],"(IR)":[3],"is":[4,174,221],"bottlenecked":[5],"by":[6,59],"the":[7,108,123,126,184,227],"scarcity":[8],"of":[9,82,92,170,187,191,230],"high-quality":[10,68],"paired":[11,27,153],"training":[12,157],"data.":[13],"Synthetic":[14],"datasets":[15,28,43],"are":[16,29],"abundant":[17],"but":[18],"often":[19],"fail":[20],"to":[21,33,66,111,133,144,225],"model":[22],"real-world":[23,26,48,72,165,185,231],"degradations,":[24],"while":[25],"expensive":[30],"and":[31,88,95,115,148,159,163,219],"difficult":[32],"capture.":[34],"As":[35],"a":[36,79,135,188,222],"result,":[37],"IR":[38,192,203,232],"models":[39,64,201],"trained":[40],"on":[41,90],"these":[42],"show":[44,179],"limited":[45],"generalization":[46,186,228],"in":[47],"scenarios.":[49],"In":[50],"this":[51],"work,":[52],"we":[53],"propose":[54],"Generative":[55],"Ground":[56],"Truth":[57],"(GGT)":[58],"using":[60],"generative":[61,200],"multimodal":[62],"foundation":[63],"(MFMs)":[65],"produce":[67],"(HQ)":[69],"targets":[70],"from":[71],"low-quality":[73],"(LQ)":[74],"images.":[75],"We":[76,129],"first":[77],"conduct":[78],"systematic":[80],"evaluation":[81],"nine":[83],"state-of-the-art":[84],"MFMs,":[85],"including":[86],"Nano-Banana-2":[87,102,132],"GPT-Image-2,":[89],"images":[91],"various":[93],"scenes":[94,162],"degradation":[96],"types.":[97],"The":[98],"results":[99,206],"demonstrate":[100],"that":[101,180,208],"with":[103,194],"VLM-based":[104],"adaptive":[105],"prompting":[106],"shows":[107],"highest":[109],"capability":[110],"synthesize":[112],"perceptually":[113],"realistic":[114],"content-faithful":[116],"HQ":[117],"targets,":[118],"which":[119,139],"can":[120,210],"serve":[121,211],"as":[122,212],"GGT":[124,136],"for":[125,198,202,215],"LQ":[127],"input.":[128],"then":[130],"employ":[131],"build":[134],"synthesis":[137],"pipeline,":[138],"involves":[140],"multi-stage":[141],"quality":[142],"control":[143],"ensure":[145],"data":[146,217],"reliability,":[147],"construct":[149],"GGT-100K,":[150],"an":[151],"LQ-HQ":[152],"dataset":[154],"comprising":[155],"103,707":[156],"pairs":[158,173],"covering":[160],"diverse":[161],"complex":[164],"degradations.":[166],"A":[167],"test":[168],"set":[169],"500":[171],"also":[175],"established.":[176],"Extensive":[177],"experiments":[178],"GGT-100K":[181,220],"consistently":[182],"improves":[183],"wide":[189],"range":[190],"models,":[193],"particularly":[195],"strong":[196],"benefits":[197],"finetuning":[199],"tasks.":[204],"Our":[205],"suggest":[207],"MFMs":[209],"practical":[213],"tools":[214],"restoration-oriented":[216],"generation,":[218],"useful":[223],"resource":[224],"expand":[226],"boundaries":[229],"models.":[233]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-02T00:00:00"}