{"id":"https://openalex.org/W7224838738","doi":"https://doi.org/10.48550/arxiv.2610.39972","title":"Blind Video Denoising for Vocal Tract rtMRI using a Self-Supervised Ensemble","display_name":"Blind Video Denoising for Vocal Tract rtMRI using a Self-Supervised Ensemble","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224838738","doi":"https://doi.org/10.48550/arxiv.2610.39972"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39972","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39972","pdf_url":"https://arxiv.org/pdf/2610.39972","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39972","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160170244","display_name":"Julian Andres Hernandez-Potes","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17937529","display_name":"German Cancer Research Center","ror":"https://ror.org/04cdgtt98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I17937529"]},{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hernandez-Potes, Julian Andres","raw_affiliation_strings":["Friedrich-Alexander- Universit\u00e4t Erlangen-N\u00fcrnberg , 91058 Erlangen , Germany","Potes is with the German Cancer Research Center (DKFZ) , 69120 Heidelberg , Germany","Toro is affiliated with the Technische Universit\u00e4t M\u00fcnchen , 80333 Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander- Universit\u00e4t Erlangen-N\u00fcrnberg , 91058 Erlangen , Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Potes is with the German Cancer Research Center (DKFZ) , 69120 Heidelberg , Germany","institution_ids":["https://openalex.org/I17937529"]},{"raw_affiliation_string":"Toro is affiliated with the Technische Universit\u00e4t M\u00fcnchen , 80333 Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015908653","display_name":"Tom\u00e1s Arias\u2010Vergara","orcid":"https://orcid.org/0000-0001-9405-4154","observed_orcids":["https://orcid.org/0000-0001-9405-4154"]},"institutions":[{"id":"https://openalex.org/I17937529","display_name":"German Cancer Research Center","ror":"https://ror.org/04cdgtt98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I17937529"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arias-Vergara, Tom\u00e1s","raw_affiliation_strings":["Potes is with the German Cancer Research Center (DKFZ) , 69120 Heidelberg , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Potes is with the German Cancer Research Center (DKFZ) , 69120 Heidelberg , Germany","institution_ids":["https://openalex.org/I17937529"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060488239","display_name":"Daiqi Liu","orcid":"https://orcid.org/0009-0001-0905-3833","observed_orcids":["https://orcid.org/0009-0001-0905-3833"]},"institutions":[{"id":"https://openalex.org/I17937529","display_name":"German Cancer Research Center","ror":"https://ror.org/04cdgtt98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I17937529"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Liu, Daiqi","raw_affiliation_strings":["Potes is with the German Cancer Research Center (DKFZ) , 69120 Heidelberg , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Potes is with the German Cancer Research Center (DKFZ) , 69120 Heidelberg , Germany","institution_ids":["https://openalex.org/I17937529"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160212984","display_name":"Andreas Maier","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17937529","display_name":"German Cancer Research Center","ror":"https://ror.org/04cdgtt98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I17937529"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maier, Andreas","raw_affiliation_strings":["Potes is with the German Cancer Research Center (DKFZ) , 69120 Heidelberg , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Potes is with the German Cancer Research Center (DKFZ) , 69120 Heidelberg , Germany","institution_ids":["https://openalex.org/I17937529"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090347814","display_name":"Paula Andrea P\u00e9rez-Toro","orcid":"https://orcid.org/0000-0002-2727-2116","observed_orcids":["https://orcid.org/0000-0002-2727-2116"]},"institutions":[{"id":"https://openalex.org/I17937529","display_name":"German Cancer Research Center","ror":"https://ror.org/04cdgtt98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I17937529"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Perez-Toro, Paula Andrea","raw_affiliation_strings":["Potes is with the German Cancer Research Center (DKFZ) , 69120 Heidelberg , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Potes is with the German Cancer Research Center (DKFZ) , 69120 Heidelberg , Germany","institution_ids":["https://openalex.org/I17937529"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9994999766349792,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":9.999999747378752e-05,"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/self-supervised-learning","display_name":"self-supervised learning","score":0.8479999899864197},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"ensemble learning","score":0.5379999876022339},{"id":"https://openalex.org/keywords/non-local-means-filter","display_name":"non-local means","score":0.8209999799728394},{"id":"https://openalex.org/keywords/variance-stabilization","display_name":"variance stabilization","score":0.75},{"id":"https://openalex.org/keywords/pseudo-supervision","display_name":"pseudo-supervision","score":0.7480000257492065},{"id":"https://openalex.org/keywords/speech-articulation","display_name":"speech articulation","score":0.5019999742507935},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.41100001335144043}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.839900016784668},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.7117999792098999},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5999000072479248},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5860999822616577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5859000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5594000220298767},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.448199987411499},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3732999861240387},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3370000123977661},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3361000120639801},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.2948000133037567},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C60472773","wikidata":"https://www.wikidata.org/wiki/Q7331156","display_name":"Rician fading","level":4,"score":0.2883000075817108},{"id":"https://openalex.org/C180940675","wikidata":"https://www.wikidata.org/wiki/Q7575045","display_name":"Speckle noise","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39972","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39972","pdf_url":"https://arxiv.org/pdf/2610.39972","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,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2610.39972","doi":"https://doi.org/10.48550/arxiv.2610.39972","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39972","pdf_url":null,"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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39972","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39972","pdf_url":"https://arxiv.org/pdf/2610.39972","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320873","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224838738.pdf","grobid_xml":"https://content.openalex.org/works/W7224838738.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2026495866","https://openalex.org/W4360602229","https://openalex.org/W4296194858","https://openalex.org/W4296068814","https://openalex.org/W2077133139","https://openalex.org/W2512440779","https://openalex.org/W2039743158","https://openalex.org/W7222394595","https://openalex.org/W7135197657","https://openalex.org/W2166344791"],"abstract_inverted_index":{"Real-time":[0],"magnetic":[1],"resonance":[2],"imaging":[3],"of":[4,79,119,142,146],"the":[5,14,85,95,98,114,140,175,186,191,196],"vocal":[6,39],"tract":[7],"makes":[8],"speech":[9],"articulation":[10],"directly":[11],"observable,":[12],"but":[13],"trade-off":[15],"between":[16],"temporal":[17],"resolution":[18],"and":[19,25,77,126,154,166,184],"signal":[20],"quality":[21],"introduces":[22],"substantial":[23],"noise":[24,75,91,135],"obscures":[26],"fine":[27],"articulatory":[28,81,111],"detail.":[29],"Since":[30],"clean":[31],"references":[32],"cannot":[33],"be":[34],"acquired":[35],"for":[36,182],"a":[37,52,65],"moving":[38],"tract,":[40],"supervised":[41],"denoising":[42,54],"approaches":[43],"are":[44],"not":[45],"applicable":[46],"in":[47,113,195],"this":[48],"setting.":[49],"We":[50],"propose":[51],"self-supervised":[53],"framework":[55],"that":[56,94,132,174,185],"combines":[57],"spatiotemporal":[58],"super-resolution":[59],"learning":[60],"with":[61],"pseudo-supervision":[62,177],"derived":[63],"from":[64],"variance-stabilized":[66,176],"non-local":[67,124,128],"means":[68,125],"filter.":[69],"A":[70],"dual-model":[71],"fusion":[72],"strategy":[73],"balances":[74],"suppression":[76,136],"preservation":[78],"high-frequency":[80,110,143],"structure.":[82],"Experiments":[83],"on":[84,104],"USC-75":[86],"multi-speaker":[87],"dataset":[88],"under":[89],"natural":[90],"conditions":[92],"show":[93],"ensemble":[96],"raises":[97],"signal-to-noise":[99,158],"ratio":[100,159],"by":[101,161],"11.9":[102],"dB":[103,165],"unseen":[105],"subjects":[106],"while":[107],"attaining":[108],"more":[109],"content":[112,144],"frames.":[115],"Among":[116],"tuned":[117],"implementations":[118],"anisotropic":[120],"diffusion,":[121],"block-matching":[122],"filtering,":[123],"pre-smoothed":[127],"means,":[129],"every":[130],"configuration":[131],"achieves":[133],"comparable":[134],"does":[137],"so":[138],"at":[139],"cost":[141],"or":[145],"structural":[147,167],"fidelity.":[148],"Under":[149],"severe":[150],"added":[151],"Gaussian,":[152],"Rayleigh":[153],"Rician":[155],"noise,":[156],"peak":[157],"improves":[160],"7.6":[162],"to":[163,190],"11.8":[164],"similarity":[168],"roughly":[169],"triples.":[170],"An":[171],"ablation":[172],"shows":[173],"is":[178,188],"an":[179],"essential":[180],"element":[181],"denoising,":[183],"effect":[187],"attributable":[189],"hard":[192],"thresholding":[193],"contained":[194],"stabilization":[197],"transform.":[198]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-10-31T00:00:00"}