{"id":"https://openalex.org/W4303440777","doi":"https://doi.org/10.48550/arxiv.2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","display_name":"Imagen Video: High Definition Video Generation with Diffusion Models","publication_year":2022,"publication_date":"2022-10-05","ids":{"openalex":"https://openalex.org/W4303440777","doi":"https://doi.org/10.48550/arxiv.2210.02303"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.02303","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.02303","pdf_url":"https://arxiv.org/pdf/2210.02303","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/2210.02303","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007990046","display_name":"Jonathan Ho","orcid":"https://orcid.org/0000-0001-9299-9824"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ho, Jonathan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036374472","display_name":"William Chan","orcid":"https://orcid.org/0000-0001-9684-888X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chan, William","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022455158","display_name":"Chitwan Saharia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saharia, Chitwan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046333438","display_name":"Jay Whang","orcid":"https://orcid.org/0009-0000-0084-5933"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Whang, Jay","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061687942","display_name":"Ruiqi Gao","orcid":"https://orcid.org/0000-0003-2657-2819"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Ruiqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083585691","display_name":"Alexey A. Gritsenko","orcid":"https://orcid.org/0000-0003-1799-2301"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gritsenko, Alexey","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024065815","display_name":"Diederik P. Kingma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kingma, Diederik P.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004918186","display_name":"Ben Poole","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Poole, Ben","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103947107","display_name":"Mohammad Norouzi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Norouzi, Mohammad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035123135","display_name":"David J. Fleet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fleet, David J.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082512329","display_name":"Tim Salimans","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salimans, Tim","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5007990046"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":346,"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":0.9948999881744385,"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":0.9948999881744385,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9700000286102295,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.9426000118255615,"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":0.8134923577308655},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5508286952972412},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.5144324898719788},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.5081379413604736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4971356689929962},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4590739905834198},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.45575398206710815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134923577308655},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5508286952972412},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.5144324898719788},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.5081379413604736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4971356689929962},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4590739905834198},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.45575398206710815},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.02303","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.02303","pdf_url":"https://arxiv.org/pdf/2210.02303","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.2210.02303","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.02303","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:2210.02303","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.02303","pdf_url":"https://arxiv.org/pdf/2210.02303","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":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1574724839","https://openalex.org/W4221117092","https://openalex.org/W2981480840","https://openalex.org/W2213155192","https://openalex.org/W2045735464","https://openalex.org/W1623638113","https://openalex.org/W2096476311","https://openalex.org/W181787362","https://openalex.org/W2406608628","https://openalex.org/W3034776505"],"abstract_inverted_index":{"We":[0,44,120],"present":[1],"Imagen":[2,21,122],"Video,":[3],"a":[4,11,18,28,34,53,136],"text-conditional":[5],"video":[6,14,30,41,100,110],"generation":[7,31,97,101],"system":[8,51],"based":[9],"on":[10,94],"cascade":[12],"of":[13,36,65,78,81,127,130,139],"diffusion":[15,82],"models.":[16,43,83],"Given":[17],"text":[19,152],"prompt,":[20],"Video":[22,123],"generates":[23],"high":[24,54,117,131,137],"definition":[25,55],"videos":[26,129,150],"using":[27],"base":[29],"model":[32,57],"and":[33,39,68,75,88,141,151,158],"sequence":[35],"interleaved":[37],"spatial":[38,69],"temporal":[40,67],"super-resolution":[42,70],"describe":[45],"how":[46],"we":[47,86,104],"scale":[48],"up":[49],"the":[50,63,76,79,99,145],"as":[52,62],"text-to-video":[56],"including":[58,144],"design":[59],"decisions":[60],"such":[61],"choice":[64,77],"fully-convolutional":[66],"models":[71,111],"at":[72],"certain":[73],"resolutions,":[74],"v-parameterization":[80],"In":[84],"addition,":[85],"confirm":[87],"transfer":[89],"findings":[90],"from":[91],"previous":[92],"work":[93],"diffusion-based":[95],"image":[96],"to":[98,108,147],"setting.":[102],"Finally,":[103],"apply":[105],"progressive":[106],"distillation":[107],"our":[109],"with":[112,159],"classifier-free":[113],"guidance":[114],"for":[115,165],"fast,":[116],"quality":[118],"sampling.":[119],"find":[121],"not":[124],"only":[125],"capable":[126],"generating":[128],"fidelity,":[132],"but":[133],"also":[134],"having":[135],"degree":[138],"controllability":[140],"world":[142],"knowledge,":[143],"ability":[146],"generate":[148],"diverse":[149],"animations":[153],"in":[154],"various":[155],"artistic":[156],"styles":[157],"3D":[160],"object":[161],"understanding.":[162],"See":[163],"https://imagen.research.google/video/":[164],"samples.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":201},{"year":2023,"cited_by_count":105},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}
