{"id":"https://openalex.org/W4387158312","doi":"https://doi.org/10.48550/arxiv.2309.15533","title":"Uncertainty Quantification via Neural Posterior Principal Components","display_name":"Uncertainty Quantification via Neural Posterior Principal Components","publication_year":2023,"publication_date":"2023-09-27","ids":{"openalex":"https://openalex.org/W4387158312","doi":"https://doi.org/10.48550/arxiv.2309.15533"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.15533","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.15533","pdf_url":"https://arxiv.org/pdf/2309.15533","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.15533","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041037692","display_name":"Elias Nehme","orcid":"https://orcid.org/0000-0003-1759-1751"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nehme, Elias","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018247048","display_name":"Omer Yair","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yair, Omer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058178036","display_name":"Tomer Michaeli","orcid":"https://orcid.org/0000-0003-0525-8054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michaeli, Tomer","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041037692"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9781000018119812,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9667999744415283,"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":0.700984537601471},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6357846260070801},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.6230073571205139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6076297163963318},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.5752905011177063},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47798746824264526},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46939602494239807},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4542437791824341},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4517291784286499},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3474876284599304},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20728585124015808},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19634363055229187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.700984537601471},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6357846260070801},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.6230073571205139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6076297163963318},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.5752905011177063},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47798746824264526},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46939602494239807},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4542437791824341},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4517291784286499},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3474876284599304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20728585124015808},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19634363055229187},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.15533","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.15533","pdf_url":"https://arxiv.org/pdf/2309.15533","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.15533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.15533","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.15533","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.15533","pdf_url":"https://arxiv.org/pdf/2309.15533","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2907830442","https://openalex.org/W2017457812","https://openalex.org/W3178025616","https://openalex.org/W2131831293","https://openalex.org/W2946160871","https://openalex.org/W3035059915","https://openalex.org/W1995073329","https://openalex.org/W2060947339","https://openalex.org/W425542480","https://openalex.org/W49967185"],"abstract_inverted_index":{"Uncertainty":[0],"quantification":[1,207],"is":[2,38,108],"crucial":[3],"for":[4,23,90,124,132],"the":[5,49,62,65,70,74,91,112,126,129,159,177],"deployment":[6],"of":[7,35,40,58,69,102,128,141,215],"image":[8,175],"restoration":[9],"models":[10],"in":[11,136,188],"safety-critical":[12],"domains,":[13],"like":[14],"autonomous":[15],"driving":[16],"and":[17,176,194,219],"biological":[18,195],"imaging.":[19],"To":[20],"date,":[21],"methods":[22],"uncertainty":[24,59,203,206],"visualization":[25],"have":[26],"mainly":[27],"focused":[28],"on":[29,82,184],"per-pixel":[30,36],"estimates.":[31],"Yet,":[32],"a":[33,86,98,122,137,142,151,173],"heatmap":[34],"variances":[37,63],"typically":[39],"little":[41],"practical":[42],"use,":[43],"as":[44],"it":[45],"does":[46],"not":[47],"capture":[48],"strong":[50],"correlations":[51],"between":[52],"pixels.":[53],"A":[54],"more":[55],"natural":[56],"measure":[57],"corresponds":[60],"to":[61,157,170],"along":[64],"principal":[66],"components":[67],"(PCs)":[68],"posterior":[71,130,178,210],"distribution.":[72],"Theoretically,":[73],"PCs":[75,127],"can":[76,147,165],"be":[77,166],"computed":[78],"by":[79],"applying":[80],"PCA":[81],"samples":[83,103],"generated":[84],"from":[85,168],"conditional":[87],"generative":[88],"model":[89,153],"input":[92,134],"image.":[93],"However,":[94],"this":[95,118],"requires":[96],"generating":[97],"very":[99],"large":[100],"number":[101],"at":[104,223],"test":[105],"time,":[106],"which":[107],"painfully":[109],"slow":[110],"with":[111,209],"current":[113],"state-of-the-art":[114],"(diffusion)":[115],"models.":[116],"In":[117],"work,":[119],"we":[120],"present":[121],"method":[123,146,183,199],"predicting":[125],"distribution":[131],"any":[133],"image,":[135],"single":[138],"forward":[139],"pass":[140],"neural":[143],"network.":[144],"Our":[145,198],"either":[148],"wrap":[149],"around":[150],"pre-trained":[152],"that":[154],"was":[155],"trained":[156,167],"minimize":[158],"mean":[160],"square":[161],"error":[162],"(MSE),":[163],"or":[164],"scratch":[169],"output":[171],"both":[172],"predicted":[174],"PCs.":[179],"We":[180],"showcase":[181],"our":[182],"multiple":[185],"inverse":[186],"problems":[187],"imaging,":[189],"including":[190],"denoising,":[191],"inpainting,":[192],"super-resolution,":[193],"image-to-image":[196],"translation.":[197],"reliably":[200],"conveys":[201],"instance-adaptive":[202],"directions,":[204],"achieving":[205],"comparable":[208],"samplers":[211],"while":[212],"being":[213],"orders":[214],"magnitude":[216],"faster.":[217],"Code":[218],"examples":[220],"are":[221],"available":[222],"https://eliasnehme.github.io/NPPC/":[224]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}