{"id":"https://openalex.org/W4366999887","doi":"https://doi.org/10.48550/arxiv.2304.11751","title":"Score-Based Diffusion Models as Principled Priors for Inverse Imaging","display_name":"Score-Based Diffusion Models as Principled Priors for Inverse Imaging","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4366999887","doi":"https://doi.org/10.48550/arxiv.2304.11751"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2304.11751","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_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2304.11751","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003656942","display_name":"Berthy T. Feng","orcid":"https://orcid.org/0000-0002-1843-2165"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Berthy T.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102669921","display_name":"Jamie Smith","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Smith, Jamie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018026577","display_name":"Michael Rubinstein","orcid":"https://orcid.org/0000-0002-5455-0951"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rubinstein, Michael","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067538672","display_name":"Hui\u2010Wen Chang","orcid":"https://orcid.org/0000-0001-8877-1886"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Huiwen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061668167","display_name":"Katherine L. Bouman","orcid":"https://orcid.org/0000-0003-0077-4367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bouman, Katherine L.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074429265","display_name":"William T. Freeman","orcid":"https://orcid.org/0000-0002-2231-7995"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Freeman, William T.","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"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":1,"citation_normalized_percentile":{"value":0.901829,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":65,"max":76},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11205","display_name":"Numerical methods in inverse problems","score":0.9372,"subfield":{"id":"https://openalex.org/subfields/2610","display_name":"Mathematical Physics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11205","display_name":"Numerical methods in inverse problems","score":0.9372,"subfield":{"id":"https://openalex.org/subfields/2610","display_name":"Mathematical Physics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9299,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9233,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"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/deblurring","display_name":"Deblurring","score":0.76049733}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.96029556},{"id":"https://openalex.org/C2777693668","wikidata":"https://www.wikidata.org/wiki/Q25053743","display_name":"Deblurring","level":5,"score":0.76049733},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6492699},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.55200815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5361481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.53041583},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4897771},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.44114488},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4306463},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.41749436},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38360253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.332317},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2091862},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.20084989},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2304.11751","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_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2304.11751","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2304.11751","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_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W69468016","https://openalex.org/W4389708677","https://openalex.org/W4321613659","https://openalex.org/W4287868071","https://openalex.org/W3124172274","https://openalex.org/W3006565005","https://openalex.org/W2964314781","https://openalex.org/W2793406240","https://openalex.org/W2611832276","https://openalex.org/W2007093222"],"abstract_inverted_index":{"Priors":[0],"are":[1],"essential":[2],"for":[3,37,84],"reconstructing":[4],"images":[5,42],"from":[6,76],"noisy":[7],"and/or":[8],"incomplete":[9],"measurements.":[10,44],"The":[11],"choice":[12],"of":[13,22,41,66],"the":[14,18,62],"prior":[15],"determines":[16],"both":[17],"quality":[19],"and":[20,53,94],"uncertainty":[21],"recovered":[23],"images.":[24],"We":[25,71],"propose":[26],"turning":[27],"score-based":[28,68,99],"diffusion":[29,69],"models":[30],"into":[31],"principled":[32,102],"image":[33,108],"priors":[34,47,100],"(\"score-based":[35],"priors\")":[36],"analyzing":[38],"a":[39,67,105],"posterior":[40],"given":[43],"Previously,":[45],"probabilistic":[46],"were":[48],"limited":[49],"to":[50,74],"handcrafted":[51],"regularizers":[52],"simple":[54],"distributions.":[55],"In":[56],"this":[57,81],"work,":[58],"we":[59],"empirically":[60],"validate":[61],"theoretically-proven":[63],"probability":[64,82],"function":[65,83],"model.":[70],"show":[72],"how":[73],"sample":[75],"resulting":[77],"posteriors":[78],"by":[79],"using":[80],"variational":[85],"inference.":[86],"Our":[87],"results,":[88],"including":[89],"experiments":[90],"on":[91],"denoising,":[92],"deblurring,":[93],"interferometric":[95],"imaging,":[96],"suggest":[97],"that":[98],"enable":[101],"inference":[103],"with":[104],"sophisticated,":[106],"data-driven":[107],"prior.":[109]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4366999887","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-04-24T02:49:21.815319","created_date":"2023-04-27"}