{"id":"https://openalex.org/W7166540328","doi":"https://doi.org/10.1109/tip.2026.3706287","title":"Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion","display_name":"Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166540328","doi":"https://doi.org/10.1109/tip.2026.3706287","pmid":"https://pubmed.ncbi.nlm.nih.gov/42371877"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3706287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3706287","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100580246","display_name":"Linxuan Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linxuan Xia","raw_affiliation_strings":["State Key Laboratory of CAD&CG, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0007-7336-4509","affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD&CG, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I55712492","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101833492","display_name":"Boxi Wu","orcid":"https://orcid.org/0000-0003-4494-193X"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boxi Wu","raw_affiliation_strings":["College of Software, Zhejiang University, Ningbo, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-4494-193X","affiliations":[{"raw_affiliation_string":"College of Software, Zhejiang University, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139569518","display_name":"Xiaolong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Yang","raw_affiliation_strings":["FiT Department, Tencent Technology (Shenzhen) Company Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FiT Department, Tencent Technology (Shenzhen) Company Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139597279","display_name":"Tianrun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrun Wu","raw_affiliation_strings":["College of Software, Zhejiang University, Ningbo, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Software, Zhejiang University, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111219486","display_name":"Yuanzhang Zhao","orcid":"https://orcid.org/0009-0003-3613-9469"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Zhao","raw_affiliation_strings":["State Key Laboratory of CAD&CG, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD&CG, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I55712492","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037942269","display_name":"Deng Cai","orcid":"https://orcid.org/0000-0001-9817-4065"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng Cai","raw_affiliation_strings":["State Key Laboratory of CAD&CG, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-9817-4065","affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD&CG, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I55712492","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107807658","display_name":"Liu W","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140439","display_name":"Digital Video (Italy)","ror":"https://ror.org/04ge7a533","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210140439"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Video Rebirth, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Video Rebirth, Hong Kong, China","institution_ids":["https://openalex.org/I4210140439"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83538609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"7249","last_page":"7260"},"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":0.45089998841285706,"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":0.45089998841285706,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.19979999959468842,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.07460000365972519,"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-processing","display_name":"Image processing","score":0.4855000078678131},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.3919000029563904},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.36480000615119934},{"id":"https://openalex.org/keywords/texture-synthesis","display_name":"Texture synthesis","score":0.35499998927116394},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3391999900341034},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33899998664855957},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3122999966144562}],"concepts":[{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4855000078678131},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45899999141693115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4440000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44209998846054077},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.3919000029563904},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.36480000615119934},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.35499998927116394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.349700003862381},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3052000105381012},{"id":"https://openalex.org/C185568154","wikidata":"https://www.wikidata.org/wiki/Q530242","display_name":"Mathematical morphology","level":4,"score":0.3041999936103821},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.2587999999523163},{"id":"https://openalex.org/C2984999661","wikidata":"https://www.wikidata.org/wiki/Q603159","display_name":"Surface fitting","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3706287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3706287","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42371877","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42371877","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1479189481","display_name":null,"funder_award_id":"622273302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1488486387","display_name":null,"funder_award_id":"62273302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2861150812","display_name":null,"funder_award_id":"62036009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6146991486","display_name":null,"funder_award_id":"62402417","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7071169373","display_name":null,"funder_award_id":"61936006","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"synthesis":[1,161,189],"is":[2,90],"a":[3,101,179],"key":[4],"application":[5],"of":[6,18],"generative":[7],"AI.":[8],"It":[9],"can":[10],"help":[11],"reduce":[12],"overfitting":[13],"and":[14,36,45,127,163],"the":[15,61,116,140],"high":[16],"cost":[17],"collecting":[19],"real-world":[20],"data":[21,86,177],"for":[22,68,105],"downstream":[23,42,70,171],"discriminative":[24],"models.":[25],"However,":[26],"current":[27],"methods":[28],"mainly":[29],"focus":[30],"on":[31,184],"making":[32],"images":[33,57],"look":[34],"realistic":[35],"ignore":[37],"their":[38,66],"true":[39],"goal:":[40],"improving":[41,69],"model":[43],"generalization":[44],"robustness.":[46],"We":[47,131,153],"find":[48],"that":[49,58,78,137],"existing":[50,168,188],"approaches":[51],"tend":[52],"to":[53,91,158],"produce":[54],"high-fidelity":[55],"synthetic":[56,85,176],"closely":[59],"resemble":[60],"original":[62],"data.":[63],"This":[64],"limits":[65],"value":[67],"task":[71],"performance.":[72],"To":[73],"overcome":[74],"this,":[75],"we":[76,99,114],"argue":[77],"diversity,":[79],"not":[80],"just":[81],"fidelity,":[82],"must":[83],"guide":[84],"generation":[87,112],"if":[88],"it":[89],"truly":[92],"complement":[93],"human-collected":[94],"datasets.":[95],"In":[96],"this":[97],"paper,":[98],"introduce":[100],"Retrieval-Augmented":[102],"Generation":[103],"framework":[104],"diverse":[106],"diffusion-based":[107],"image":[108,142,160],"synthesis.":[109],"At":[110],"each":[111],"step,":[113],"retrieve":[115],"top-K":[117],"most":[118],"similar":[119],"samples":[120,147],"in":[121,148],"feature":[122,149],"space":[123],"from":[124,144],"both":[125],"real":[126],"previously":[128],"generated":[129],"images.":[130],"then":[132],"apply":[133],"an":[134],"Anti-Attention":[135],"mechanism":[136],"actively":[138],"pushes":[139],"new":[141],"away":[143],"these":[145],"retrieved":[146],"space,":[150],"maximizing":[151],"dissimilarity.":[152],"propose":[154],"novel":[155],"evaluation":[156],"metrics":[157],"assess":[159],"diversity":[162],"demonstrate":[164],"significant":[165],"improvements":[166],"over":[167],"benchmarks.":[169],"Moreover,":[170],"models":[172],"trained":[173],"with":[174],"our":[175],"achieved":[178],"1.9%":[180],"absolute":[181],"accuracy":[182],"gain":[183],"standard":[185],"benchmarks,":[186],"outperforming":[187],"techniques.":[190]},"counts_by_year":[],"updated_date":"2026-07-14T05:46:48.188703","created_date":"2026-06-30T00:00:00"}