{"id":"https://openalex.org/W4293327156","doi":"https://doi.org/10.48550/arxiv.2208.11970","title":"Understanding Diffusion Models: A Unified Perspective","display_name":"Understanding Diffusion Models: A Unified Perspective","publication_year":2022,"publication_date":"2022-08-25","ids":{"openalex":"https://openalex.org/W4293327156","doi":"https://doi.org/10.48550/arxiv.2208.11970"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2208.11970","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.11970","pdf_url":"https://arxiv.org/pdf/2208.11970","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.11970","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059795370","display_name":"Calvin Luo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Luo, Calvin","raw_affiliation_strings":["Google Research , Brain Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research , Brain Team","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5059795370"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":509,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9955999851226807,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9955999851226807,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.0010999999940395355,"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/diffusion-models","display_name":"diffusion models","score":0.9990000128746033},{"id":"https://openalex.org/keywords/hierarchical-variational-autoencoder","display_name":"hierarchical variational autoencoder","score":0.9010000228881836},{"id":"https://openalex.org/keywords/conditional-diffusion-models","display_name":"conditional diffusion models","score":0.515999972820282},{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.9169999957084656}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6525660157203674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6435329914093018},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.642332136631012},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5865577459335327},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5708079934120178},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.536381185054779},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5065654516220093},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5054073333740234},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48284250497817993},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46519315242767334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45251205563545227},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.44903090596199036},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41518712043762207},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.362177312374115},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36212730407714844},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3482062816619873},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3332001566886902},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32897159457206726},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28185439109802246},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27518564462661743},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08639267086982727},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2208.11970","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.11970","pdf_url":"https://arxiv.org/pdf/2208.11970","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2208.11970","doi":"https://doi.org/10.48550/arxiv.2208.11970","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2208.11970","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:2208.11970","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.11970","pdf_url":"https://arxiv.org/pdf/2208.11970","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293327156.pdf","grobid_xml":"https://content.openalex.org/works/W4293327156.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2804821933","https://openalex.org/W3110257065","https://openalex.org/W3119280808","https://openalex.org/W4224035735","https://openalex.org/W4281485151"],"related_works":["https://openalex.org/W3217132494","https://openalex.org/W4405029513","https://openalex.org/W4402712366","https://openalex.org/W3169386841","https://openalex.org/W6963345156","https://openalex.org/W4400449735","https://openalex.org/W4416350467","https://openalex.org/W7214977431","https://openalex.org/W7160392866","https://openalex.org/W7169848782"],"abstract_inverted_index":{"Diffusion":[0,49],"models":[1,15,38,171],"have":[2],"shown":[3],"incredible":[4],"capabilities":[5],"as":[6,21,52],"generative":[7],"models;":[8],"indeed,":[9],"they":[10],"power":[11],"the":[12,34,73,96,106,116,138,143,152],"current":[13],"state-of-the-art":[14],"on":[16],"text-conditioned":[17],"image":[18],"generation":[19],"such":[20],"Imagen":[22],"and":[23,32,42,69,141],"DALL-E":[24],"2.":[25],"In":[26],"this":[27],"work":[28],"we":[29,161],"review,":[30],"demystify,":[31],"unify":[33],"understanding":[35],"of":[36,56,72,92,104,119,146],"diffusion":[37,148,170],"across":[39],"both":[40],"variational":[41,144],"score-based":[43],"perspectives.":[44],"We":[45,75,128],"first":[46],"derive":[47],"Variational":[48,60],"Models":[50],"(VDM)":[51],"a":[53,57,80,86,120,147,166],"special":[54],"case":[55],"Markovian":[58],"Hierarchical":[59],"Autoencoder,":[61],"where":[62],"three":[63,93],"key":[64],"assumptions":[65],"enable":[66],"tractable":[67],"computation":[68],"scalable":[70],"optimization":[71],"ELBO.":[74],"then":[76,129],"prove":[77],"that":[78],"optimizing":[79],"VDM":[81],"boils":[82],"down":[83],"to":[84,89,136,164],"learning":[85],"neural":[87],"network":[88],"predict":[90],"one":[91],"potential":[94],"objectives:":[95],"original":[97,107],"source":[98,108],"input":[99,122],"from":[100,110],"any":[101,111,124],"arbitrary":[102,125],"noisification":[103],"it,":[105],"noise":[109,126],"arbitrarily":[112],"noisified":[113,121],"input,":[114],"or":[115],"score":[117,139],"function":[118],"at":[123],"level.":[127],"dive":[130],"deeper":[131],"into":[132],"what":[133],"it":[134],"means":[135],"learn":[137,165],"function,":[140],"connect":[142],"perspective":[145,156],"model":[149],"explicitly":[150],"with":[151],"Score-based":[153],"Generative":[154],"Modeling":[155],"through":[157],"Tweedie's":[158],"Formula.":[159],"Lastly,":[160],"cover":[162],"how":[163],"conditional":[167],"distribution":[168],"using":[169],"via":[172],"guidance.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":101},{"year":2025,"cited_by_count":176},{"year":2024,"cited_by_count":148},{"year":2023,"cited_by_count":78},{"year":2022,"cited_by_count":6}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2022-08-27T00:00:00"}