{"id":"https://openalex.org/W6887346151","doi":"https://doi.org/10.15496/publikation-97202","title":"Enhancement and Evaluation of Deep Generative Networks with Applications in Super-Resolution and Image Generation","display_name":"Enhancement and Evaluation of Deep Generative Networks with Applications in Super-Resolution and Image Generation","publication_year":2024,"publication_date":"2024-07-30","ids":{"openalex":"https://openalex.org/W6887346151","doi":"https://doi.org/10.15496/publikation-97202"},"language":"en","primary_location":{"id":"doi:10.15496/publikation-97202","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-97202","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":[],"is_oa":false,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.15496/publikation-97202","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sajjadi, Seyed Mohammad Mehdi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sajjadi, Seyed Mohammad Mehdi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"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":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5512999892234802},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5490000247955322},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.48890000581741333},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4108999967575073},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.4034000039100647},{"id":"https://openalex.org/keywords/raster-graphics","display_name":"Raster graphics","score":0.37380000948905945},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.3716999888420105},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3709999918937683},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics","score":0.36559998989105225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954999804496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7192999720573425},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5512999892234802},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5169000029563904},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4034000039100647},{"id":"https://openalex.org/C181844469","wikidata":"https://www.wikidata.org/wiki/Q182270","display_name":"Raster graphics","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3716999888420105},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.36419999599456787},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C27405340","wikidata":"https://www.wikidata.org/wiki/Q440296","display_name":"Image scaling","level":4,"score":0.30059999227523804},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.15496/publikation-97202","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-97202","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":[],"is_oa":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.15496/publikation-97202","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-97202","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":[],"is_oa":false,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4223926365375519}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Since":[0],"the":[1,6,20,46,68,91,101,132,138,173,239,244,257,260,265,314,339,348,358,398,433],"advent":[2],"of":[3,14,31,48,60,70,95,121,160,165,175,201,220,259,316,336,341,355,360,378,391,393,397],"computers,":[4],"perceiving":[5],"world":[7],"visually":[8],"has":[9,114],"been":[10],"a":[11,127,143,157,199,205,212,252,285,306,317,367,389,407],"major":[12,34,218,422],"focus":[13,130],"research.":[15],"Today,":[16],"raster":[17],"graphics":[18],"are":[19,109,284,428,436],"most":[21],"popular":[22],"format":[23],"for":[24,41,347,385,432],"storing":[25],"arbitrary":[26],"visual":[27,72,181],"data.":[28,73],"This":[29,74],"choice":[30],"representation":[32],"carries":[33],"advantages,":[35],"primarily":[36,115],"high":[37],"flexibility":[38],"and":[39,86,89,93,150,168,238,280,350,383,411,417,441],"suitability":[40],"hardware":[42],"acceleration.":[43],"However,":[44],"increasing":[45],"size":[47],"images":[49],"leads":[50,177],"to":[51,66,131,136,172,178,191,263,291,298,309,325,329,365,439],"well-":[52],"known":[53,364],"blurring":[54],"or":[55],"pixelization":[56],"artifacts.":[57],"The":[58,217,268,421],"field":[59],"super":[61],"resolution":[62],"(SR)":[63],"investigates":[64],"methods":[65,108,190,362],"improve":[67],"quality":[69,153,274,392],"enlarged":[71],"work":[75],"is":[76,194,209,233,363,424],"structured":[77],"into":[78,204,409],"two":[79],"sections:":[80],"making":[81],"strides":[82],"towards":[83],"more":[84,327],"realistic":[85],"efficient":[87],"SR,":[88],"improving":[90,118,277,345,352],"architecture":[92],"evaluation":[94],"deep":[96,122],"generative":[97],"models":[98],"that":[99,146,208,254,320,425],"form":[100],"foundation":[102],"on":[103,117],"which":[104,387],"today\u2019s":[105],"best":[106],"SR":[107,155,176,189,273],"built.":[110],"While":[111],"prior":[112],"art":[113],"focused":[116],"network":[119,207],"architechtures":[120],"neural":[123,206],"networks,":[124],"we":[125],"propose":[126,247,302],"shift":[128],"in":[129,154,211,225,243,344],"loss":[133],"functions":[134],"used":[135],"train":[137],"models.":[139],"We":[140,246,301,380,402],"present":[141],"EnhanceNet,":[142],"novel":[144,158,307],"method":[145,253,269,286],"achieves":[147,270],"state-of-the-art":[148,271],"quantitative":[149],"qualitative":[151],"image":[152,188],"through":[156,197,313],"set":[159,437],"training":[161,312],"objectives.":[162],"A":[163,334],"combination":[164],"perceptual,":[166],"style,":[167],"adversarial":[169],"networks":[170],"applied":[171,210],"task":[174,434],"previously":[179],"unattainable":[180],"fidelity":[182],"at":[183],"large":[184],"scaling":[185],"factors.":[186],"Extending":[187],"video":[192,272],"data":[193,323,400],"regularly":[195,293],"achieved":[196],"feeding":[198],"number":[200],"neighbouring":[202],"frames":[203],"sliding":[213],"window":[214],"across":[215],"time.":[216],"shortcoming":[219],"this":[221],"common":[222],"approach":[223],"lies":[224],"its":[226],"low":[227],"computational":[228,278],"efficiency":[229],"as":[230,287,289,370],"each":[231],"frame":[232,262],"processed":[234],"independently":[235],"several":[236,418],"times,":[237],"resulting":[240],"temporal":[241,281],"instabilities":[242],"outputs.":[245],"Frame-Recurrent":[248],"Video":[249],"Super":[250],"Resolution,":[251],"recurrently":[255],"uses":[256],"output":[258],"last":[261],"upsample":[264],"next":[266],"one.":[267],"while":[275],"vastly":[276],"requirements":[279],"consistency.":[282],"GANs":[283],"powerful,":[288],"difficult":[290],"train,":[292],"suffering":[294],"from":[295,395],"failures":[296],"due":[297],"bad":[299],"gradients.":[300],"Tempered":[303],"Adversarial":[304],"Networks,":[305],"way":[308],"auto-stabilize":[310],"GAN":[311],"introduction":[315],"lens":[318],"module":[319],"modifies":[321],"real":[322],"samples":[324,394],"look":[326],"similar":[328],"generated":[330],"ones":[331],"throughout":[332],"training.":[333,356],"range":[335],"experiments":[337],"shows":[338],"promise":[340],"such":[342],"techniques":[343],"gradients":[346],"generator":[349],"therefore":[351],"success":[353,359],"rates":[354],"Measuring":[357],"these":[361],"be":[366],"challenging":[368],"task,":[369],"it":[371],"implies":[372],"matching":[373],"distributions":[374],"rather":[375],"than":[376],"pairs":[377],"samples.":[379],"define":[381],"Precision":[382],"Recall":[384],"Distributions":[386],"disentangles":[388],"measure":[390],"coverage":[396],"original":[399],"distribution.":[401],"close":[403],"with":[404],"Regularized":[405],"AutoEncoders,":[406],"study":[408],"differences":[410],"similarities":[412],"between":[413],"Auto":[414],"Encoders,":[415],"VAEs":[416,427],"forms":[419],"inbetween.":[420],"finding":[423],"stochastic":[426,447],"not":[429],"always":[430],"required":[431],"they":[435],"out":[438],"solve,":[440],"simpler":[442],"RAEs":[443],"often":[444],"outperform":[445],"their":[446],"counterparts.":[448]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}