{"id":"https://openalex.org/W4411948655","doi":"https://doi.org/10.1109/tcsvt.2025.3585092","title":"Leveraging Vision-Language Models to Select Trustworthy Super-Resolution Samples Generated by Diffusion Models","display_name":"Leveraging Vision-Language Models to Select Trustworthy Super-Resolution Samples Generated by Diffusion Models","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4411948655","doi":"https://doi.org/10.1109/tcsvt.2025.3585092"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3585092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3585092","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.20832","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118791732","display_name":"Cansu Korkmaz","orcid":"https://orcid.org/0000-0002-6841-4360"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Cansu Korkmaz","raw_affiliation_strings":["Department of Electrical and Electronics Engineering and the KUIS AI Center, Koç University, Istanbul, Türkiye","Department of Electrical and Electronics Engineering, KUIS AI Center, Koç University, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-6841-4360","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronics Engineering and the KUIS AI Center, Koç University, Istanbul, Türkiye","institution_ids":["https://openalex.org/I1351752"]},{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, KUIS AI Center, Koç University, Istanbul, Turkey","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034648478","display_name":"A. Murat Tekalp","orcid":"https://orcid.org/0000-0003-1465-8121"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"A. Murat Tekalp","raw_affiliation_strings":["Department of Electrical and Electronics Engineering and the KUIS AI Center, Koç University, Istanbul, Türkiye","Department of Electrical and Electronics Engineering, KUIS AI Center, Koç University, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0003-1465-8121","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronics Engineering and the KUIS AI Center, Koç University, Istanbul, Türkiye","institution_ids":["https://openalex.org/I1351752"]},{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, KUIS AI Center, Koç University, Istanbul, Turkey","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077107407","display_name":"Zafer Do\u011fan","orcid":"https://orcid.org/0000-0002-5078-4590"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Zafer Do\u011fan","raw_affiliation_strings":["Department of Electrical and Electronics Engineering and the KUIS AI Center, Koç University, Istanbul, Türkiye","Department of Electrical and Electronics Engineering, KUIS AI Center, Koç University, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-5078-4590","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronics Engineering and the KUIS AI Center, Koç University, Istanbul, Türkiye","institution_ids":["https://openalex.org/I1351752"]},{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, KUIS AI Center, Koç University, Istanbul, Turkey","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1351752"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12011159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"2","first_page":"1419","last_page":"1432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9204999804496765,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9204999804496765,"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-science","display_name":"Computer science","score":0.7516823410987854},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.7044451236724854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5767680406570435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5684459805488586},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5016944408416748},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.4298252463340759},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3762143850326538},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3243215084075928},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2107940912246704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516823410987854},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.7044451236724854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5767680406570435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5684459805488586},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5016944408416748},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.4298252463340759},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3762143850326538},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3243215084075928},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2107940912246704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2025.3585092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3585092","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2506.20832","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.20832","pdf_url":"https://arxiv.org/pdf/2506.20832","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.20832","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.20832","pdf_url":"https://arxiv.org/pdf/2506.20832","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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/G285847191","display_name":null,"funder_award_id":"118C337","funder_id":"https://openalex.org/F4320322626","funder_display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu"},{"id":"https://openalex.org/G6419087451","display_name":null,"funder_award_id":"120C156","funder_id":"https://openalex.org/F4320322626","funder_display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu"}],"funders":[{"id":"https://openalex.org/F4320322626","display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","ror":"https://ror.org/04w9kkr77"},{"id":"https://openalex.org/F4320322628","display_name":"T\u00fcrkiye Bilimler Akademisi","ror":"https://ror.org/00aqt9352"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2362774332","https://openalex.org/W4249245269","https://openalex.org/W2765548132","https://openalex.org/W2025681766","https://openalex.org/W2542402767","https://openalex.org/W3023086044","https://openalex.org/W2294441925","https://openalex.org/W2142226356","https://openalex.org/W3210000161","https://openalex.org/W3103111272"],"abstract_inverted_index":{"Super-resolution":[0],"(SR)":[1],"is":[2],"an":[3],"ill-posed":[4],"inverse":[5],"problem":[6],"with":[7,14,122,207,260],"many":[8],"feasible":[9],"solutions":[10],"that":[11,44,170,203,217],"are":[12,120,140],"consistent":[13],"a":[15,34,63,81,86,98,145,150,163,196,241,269],"given":[16],"low-resolution":[17],"image.":[18],"On":[19,56],"one":[20],"hand,":[21,59],"regressive":[22],"SR":[23,67,95,138,172,254,276],"models":[24,61,109],"aim":[25],"to":[26,32,42,125,143,226,235],"balance":[27],"fidelity":[28],"and":[29,117,131,191,213,216,232,244,263],"perceptual":[30],"quality":[31],"yield":[33,144,221],"single":[35,146],"solution;":[36],"but":[37,69],"this":[38,78,266],"trade-off":[39],"often":[40],"leads":[41],"artifacts":[43],"introduce":[45],"ambiguity":[46],"in":[47,149,210,274],"information-critical":[48],"applications":[49],"such":[50,113],"as":[51,114],"identifying":[52,91],"digits":[53],"or":[54],"letters.":[55],"the":[57,72,92,103,132,156,249,252],"other":[58],"diffusion":[60,253],"generate":[62],"diverse":[64],"set":[65,79,100],"of":[66,77,107,134,158,251],"images;":[68],"now":[70],"selecting":[71],"most":[73,93],"trustworthy":[74,94,147],"solution":[75,246],"out":[76],"becomes":[80],"challenge.":[82],"This":[83],"paper":[84],"introduces":[85],"robust,":[87],"automated":[88],"framework":[89],"for":[90,247,272],"sample":[96],"from":[97],"diffusion-generated":[99],"by":[101],"leveraging":[102],"semantic":[104,127,179,264],"reasoning":[105],"capabilities":[106],"vision-language":[108],"(VLMs).":[110],"Specifically,":[111],"VLMs":[112],"BLIP-2,":[115],"GPT-4o,":[116],"their":[118],"variants":[119],"prompted":[121],"structured":[123],"queries":[124],"evaluate":[126],"correctness,":[128,265],"visual":[129],"quality,":[130],"presence":[133],"artifacts.":[135],"The":[136],"top-ranked":[137],"candidates":[139],"then":[141],"ensembled":[142],"output":[148],"cost-effective":[151],"manner.":[152],"To":[153],"rigorously":[154],"assess":[155],"validity":[157],"VLM-selected":[159],"samples,":[160],"we":[161],"propose":[162],"novel":[164],"Trustworthiness":[165],"Score":[166],"(TWS)\u2014a":[167],"hybrid":[168],"metric":[169],"quantifies":[171],"reliability":[173],"based":[174],"on":[175,188],"three":[176],"complementary":[177],"components:":[178],"similarity":[180],"using":[181],"CLIP":[182],"embeddings,":[183],"structural":[184],"integrity":[185],"via":[186],"SSIM":[187],"edge":[189],"maps,":[190],"artifact":[192],"sensitivity":[193],"measured":[194],"through":[195],"multi-level":[197],"wavelet":[198],"decomposition.":[199],"We":[200],"empirically":[201],"demonstrate":[202],"TWS":[204,223],"correlates":[205],"strongly":[206],"human":[208,261],"preference":[209],"both":[211],"ambiguous":[212],"natural":[214],"images,":[215],"VLM-guided":[218],"selections":[219],"consistently":[220],"high":[222],"values.":[224],"Compared":[225],"conventional":[227],"metrics":[228],"like":[229],"PSNR,":[230],"LPIPS,":[231],"DISTS\u2014which":[233],"fail":[234],"reflect":[236],"information":[237],"fidelity\u2014our":[238],"approach":[239],"offers":[240],"principled,":[242],"scalable,":[243],"generalizable":[245],"navigating":[248],"uncertainty":[250],"space.":[255],"By":[256],"aligning":[257],"model":[258],"outputs":[259],"expectations":[262],"work":[267],"sets":[268],"new":[270],"benchmark":[271],"trustworthiness":[273],"generative":[275],"tasks.":[277]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}