{"id":"https://openalex.org/W7155532574","doi":"https://doi.org/10.48550/arxiv.2604.21066","title":"Optimizing Diffusion Priors in Image Reconstruction from a Single Observation","display_name":"Optimizing Diffusion Priors in Image Reconstruction from a Single Observation","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155532574","doi":"https://doi.org/10.48550/arxiv.2604.21066"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.21066","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21066","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.21066","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134473274","display_name":"Frederic Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Frederic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134487081","display_name":"Katherine L. Bouman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bouman, Katherine L.","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":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":false,"primary_topic":{"id":"https://openalex.org/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.3799999952316284,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.3799999952316284,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09799999743700027,"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/T11183","display_name":"Advanced X-ray Imaging Techniques","score":0.05849999934434891,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.9376999735832214},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7042999863624573},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6559000015258789},{"id":"https://openalex.org/keywords/deblurring","display_name":"Deblurring","score":0.5404000282287598},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.5034000277519226},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48919999599456787},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4293999969959259},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.41260001063346863}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.9376999735832214},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7042999863624573},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6559000015258789},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5465999841690063},{"id":"https://openalex.org/C2777693668","wikidata":"https://www.wikidata.org/wiki/Q25053743","display_name":"Deblurring","level":5,"score":0.5404000282287598},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49149999022483826},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48919999599456787},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4293999969959259},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4163999855518341},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.34850001335144043},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C55128770","wikidata":"https://www.wikidata.org/wiki/Q5275440","display_name":"Diffusion map","level":4,"score":0.2770000100135803},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.26089999079704285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.21066","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21066","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.21066","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21066","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"diffusion":[1,37,86,164],"priors":[2,87,137,169],"generate":[3],"high-quality":[4],"posterior":[5,157,177],"samples":[6],"across":[7],"many":[8,57],"inverse":[9,108],"problems,":[10,109],"they":[11],"are":[12],"often":[13,134],"trained":[14,142],"on":[15,40,106,143],"limited":[16],"training":[17],"sets":[18],"or":[19],"purely":[20],"simulated":[21],"data,":[22],"thus":[23,60],"inheriting":[24],"the":[25,65,95,99,115,131,149,172,175],"errors":[26],"and":[27,59,93,122,162],"biases":[28],"of":[29,44,174],"these":[30],"underlying":[31],"sources.":[32],"Current":[33],"approaches":[34],"to":[35,54,62],"finetuning":[36],"models":[38],"rely":[39],"a":[41,72,76,80,89,120,144],"large":[42],"number":[43],"observations":[45],"with":[46,125],"varying":[47],"forward":[48],"operators,":[49],"which":[50],"can":[51],"be":[52],"difficult":[53],"collect":[55],"for":[56,74],"applications,":[58],"lead":[61],"overfitting":[63],"when":[64],"measurement":[66],"set":[67],"is":[68,118,133],"small.":[69],"We":[70,102,128],"propose":[71],"method":[73,105],"tuning":[75],"prior":[77,92,117,150],"from":[78,159],"only":[79],"single":[81,90,145],"observation":[82],"by":[83,136],"combining":[84],"existing":[85],"into":[88],"product-of-experts":[91],"identifying":[94],"exponents":[96],"that":[97,130,138,170],"maximize":[98],"Bayesian":[100],"evidence.":[101],"validate":[103],"our":[104,154],"real-world":[107],"including":[110],"black":[111],"hole":[112],"imaging,":[113],"where":[114],"true":[116],"unknown":[119],"priori,":[121],"image":[123,178],"deblurring":[124],"text-conditioned":[126],"priors.":[127],"find":[129],"evidence":[132],"maximized":[135],"extend":[139],"beyond":[140],"those":[141],"dataset.":[146],"By":[147],"generalizing":[148],"through":[151],"exponent":[152],"weighting,":[153],"approach":[155],"enables":[156],"sampling":[158],"both":[160],"tempered":[161],"combined":[163],"models,":[165],"yielding":[166],"more":[167],"flexible":[168],"improve":[171],"trustworthiness":[173],"resulting":[176],"distribution.":[179]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-25T00:00:00"}