{"id":"https://openalex.org/W6929823868","doi":"https://doi.org/10.5075/epfl-thesis-7360","title":"From Classical to Unsupervised-Deep-Learning Methods for Solving Inverse Problems in Imaging.","display_name":"From Classical to Unsupervised-Deep-Learning Methods for Solving Inverse Problems in Imaging.","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W6929823868","doi":"https://doi.org/10.5075/epfl-thesis-7360"},"language":"en","primary_location":{"id":"pmh:oai:infoscience.epfl.ch:280353","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/172083","pdf_url":"http://infoscience.epfl.ch/record/280353","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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":"","raw_type":"doctoral thesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/280353","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gupta, Harshit","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gupta, Harshit","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":true,"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":{"id":"https://openalex.org/T11093","display_name":"Personality Disorders and Psychopathology","score":0.7211999893188477,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11093","display_name":"Personality Disorders and Psychopathology","score":0.7211999893188477,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.04230000078678131,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.021400000900030136,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.5519000291824341},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.54830002784729},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5299000144004822},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.4860000014305115},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.48260000348091125},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.39079999923706055},{"id":"https://openalex.org/keywords/tikhonov-regularization","display_name":"Tikhonov regularization","score":0.35749998688697815},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.35580000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6261000037193298},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.54830002784729},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.490200012922287},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.4860000014305115},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.48260000348091125},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.428600013256073},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38929998874664307},{"id":"https://openalex.org/C152442038","wikidata":"https://www.wikidata.org/wiki/Q2778212","display_name":"Tikhonov regularization","level":3,"score":0.35749998688697815},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32519999146461487},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30230000615119934},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26170000433921814}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:infoscience.epfl.ch:280353","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/172083","pdf_url":"http://infoscience.epfl.ch/record/280353","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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":"","raw_type":"doctoral thesis"},{"id":"doi:10.5075/epfl-thesis-7360","is_oa":true,"landing_page_url":"https://doi.org/10.5075/epfl-thesis-7360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dissertation"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:280353","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/172083","pdf_url":"http://infoscience.epfl.ch/record/280353","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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":"","raw_type":"doctoral thesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6929823868.pdf","grobid_xml":"https://content.openalex.org/works/W6929823868.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,113,215],"this":[1],"thesis,":[2],"we":[3,250,369],"propose":[4,158,204,353],"new":[5],"algorithms":[6,60,94,124,161,170,271],"to":[7,18,44,68,104,136,171,198,254,257,320,331,399,414,448],"solve":[8,172],"inverse":[9,177],"problems":[10,22,126,178],"in":[11,37,118,235,340,384],"the":[12,28,31,38,57,63,137,173,188,191,200,240,246,252,268,297,315,333,381,407,427,430],"context":[13],"of":[14,27,30,48,65,120,156,176,291,299,308,404,406,419,432],"biomedical":[15],"images.":[16,33,50,292,350],"Due":[17],"ill-posedness,":[19],"solving":[20],"these":[21,49,98,102],"require":[23,85,163],"some":[24,262],"prior":[25,41,165],"knowledge":[26,42],"statistics":[29,71],"underlying":[32],"The":[34,153,326,388,444],"traditional":[35],"algorithms,":[36],"field,":[39],"assume":[40],"related":[43],"smoothness":[45],"or":[46],"sparsity":[47],"Recently,":[51],"they":[52],"have":[53,82,400],"been":[54],"outperformed":[55],"by":[56,364],"second":[58,212],"generation":[59,79,213,270],"which":[61,84,95],"harness":[62],"power":[64],"neural":[66,219,302,434],"networks":[67,367],"learn":[69],"required":[70],"from":[72,122,422],"training":[73,87,89,229],"data.":[74,90,424],"Even":[75],"more":[76,111],"recently,":[77],"last":[78,154],"deep-learning-based":[80,159],"methods":[81],"emerged":[83],"neither":[86],"nor":[88],"This":[91,264],"thesis":[92],"devises":[93],"progress":[96],"through":[97],"generations.":[99],"It":[100],"extends":[101],"generations":[103],"novel":[105,280,355],"formulations":[106],"and":[107,130,142,183,194,231,346,396,453],"applications":[108],"while":[109],"bringing":[110],"robustness.":[112],"parallel,":[114],"it":[115],"also":[116],"progresses":[117],"terms":[119],"complexity,":[121],"proposing":[123],"for":[125,272,284,358],"with":[127,139,179,305,437],"1D":[128,324],"data":[129,141,334,383],"an":[131,143,205,300],"exact":[132],"known":[133],"forward":[134,146],"model":[135],"ones":[138],"4D":[140],"unknown":[144],"parametric":[145],"model.":[147],"We":[148,168,186,203,277,293,336,352,411,425],"introduce":[149],"five":[150],"main":[151],"contributions.":[152],"three":[155],"them":[157,295],"latest-generation":[160],"that":[162,207,286,376],"no":[164,393],"training.":[166],"1)":[167],"develop":[169,278],"continuous-domain":[174],"formulation":[175],"both":[180],"classical":[181],"Tikhonov":[182],"total-variation":[184],"regularizations.":[185],"formalize":[187],"problems,":[189],"characterize":[190],"solution":[192],"set,":[193,230],"devise":[195],"numerical":[196],"approaches":[197],"find":[199],"solutions.":[201],"2)":[202],"algorithm":[206,283,389],"improves":[208],"upon":[209],"end-to-end":[210],"neural-network-based":[211],"algorithms.":[214],"our":[216],"method,":[217],"a":[218,225,228,237,258,279,288,306,323,354,371,385,401,420,433,441],"network":[220,303,327,435],"is":[221,232,248,328,390,397,446],"first":[222],"trained":[223],"as":[224,236,296,429],"projector":[226,238],"on":[227,322,440],"then":[233,329],"plugged":[234],"inside":[239],"projected":[241],"gradient":[242],"descent":[243],"(PGD).":[244],"Since":[245],"problem":[247],"nonconvex,":[249],"relax":[251],"PGD":[253],"ensure":[255],"convergence":[256],"local":[259],"minimum":[260],"under":[261],"constraints.":[263],"method":[265,445],"outperforms":[266],"all":[267],"previous":[269],"Computed":[273],"Tomography":[274],"(CT).":[275],"3)":[276],"time-dependent":[281],"deep-image-prior":[282],"modalities":[285],"involve":[287],"temporal":[289,313],"sequence":[290,307],"parameterize":[294,426],"output":[298,431],"untrained":[301],"fed":[304,436],"latent":[309,316,438],"variables.":[310],"To":[311],"impose":[312],"directionality,":[314],"variables":[317,439],"are":[318],"assumed":[319],"lie":[321],"manifold.":[325,443],"tuned":[330],"minimize":[332],"fidelity.":[335],"obtain":[337],"state-of-the-art":[338],"results":[339],"dynamic":[341],"magnetic":[342],"resonance":[343],"imaging":[344],"(MRI)":[345],"even":[347],"recover":[348,449],"intra-frame":[349],"4)":[351],"reconstruction":[356],"paradigm":[357],"cryo-electron-microscopy":[359],"(CryoEM)":[360],"called":[361],"CryoGAN.":[362],"Motivated":[363],"generative":[365],"adversarial":[366],"(GANs),":[368],"reconstruct":[370,415],"biomolecule's":[372],"3D":[373],"structure":[374,421],"such":[375],"its":[377],"CryoEM":[378],"measurements":[379],"resemble":[380],"acquired":[382],"distributional":[386],"sense.":[387],"pose-or-likelihood-estimation-free,":[391],"needs":[392],"ab":[394],"initio,":[395],"proven":[398],"theoretical":[402],"guarantee":[403],"recovery":[405],"true":[408],"structure.":[409],"5)":[410],"extend":[412],"CryoGAN":[413],"continuously":[416],"varying":[417],"conformations":[418,428,452],"heterogeneous":[423],"low-dimensional":[442],"shown":[447],"continuous":[450],"protein":[451],"their":[454],"energy":[455],"landscape.":[456]},"counts_by_year":[],"updated_date":"2026-07-23T05:56:39.545243","created_date":"2025-10-10T00:00:00"}