{"id":"https://openalex.org/W7161148064","doi":"https://doi.org/10.1016/j.vrih.2026.03.002","title":"From architecture to evaluation: A comprehensive review of video generation techniques","display_name":"From architecture to evaluation: A comprehensive review of video generation techniques","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7161148064","doi":"https://doi.org/10.1016/j.vrih.2026.03.002"},"language":"en","primary_location":{"id":"doi:10.1016/j.vrih.2026.03.002","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.vrih.2026.03.002","pdf_url":null,"source":{"id":"https://openalex.org/S4210224695","display_name":"Virtual Reality & Intelligent Hardware","issn_l":"2096-5796","issn":["2096-5796","2666-1209"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Virtual Reality & Intelligent Hardware","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.vrih.2026.03.002","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136168328","display_name":"Rong ZHANG","orcid":null},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong ZHANG","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou 310018, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou 310018, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136095729","display_name":"Chi WANG","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi WANG","raw_affiliation_strings":["State Key Lab of CAD&CG, Zhejiang University, Hangzhou 310058, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou 310058, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014108776","display_name":"Ge Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojun LEI","raw_affiliation_strings":["State Key Lab of CAD&CG, Zhejiang University, Hangzhou 310058, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou 310058, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037315703","display_name":"Wenying Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weiwei XU","raw_affiliation_strings":["State Key Lab of CAD&CG, Zhejiang University, Hangzhou 310058, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou 310058, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037315703"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94640846,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"2","first_page":"172","last_page":"201"},"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":0.8712999820709229,"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":0.8712999820709229,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.046799998730421066,"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/T11448","display_name":"Face recognition and analysis","score":0.01140000019222498,"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/field","display_name":"Field (mathematics)","score":0.5383999943733215},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5328999757766724},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5178999900817871},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.48089998960494995},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41839998960494995},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.35580000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7645999789237976},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5383999943733215},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5328999757766724},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5178999900817871},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.42289999127388},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3790000081062317},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3418000042438507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33880001306533813},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.vrih.2026.03.002","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.vrih.2026.03.002","pdf_url":null,"source":{"id":"https://openalex.org/S4210224695","display_name":"Virtual Reality & Intelligent Hardware","issn_l":"2096-5796","issn":["2096-5796","2666-1209"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Virtual Reality & Intelligent Hardware","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cce5186b190f4db9aea31ff34e3f9716","is_oa":true,"landing_page_url":"https://doaj.org/article/cce5186b190f4db9aea31ff34e3f9716","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Virtual Reality & Intelligent Hardware, Vol 8, Iss 2, Pp 172-201 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.vrih.2026.03.002","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.vrih.2026.03.002","pdf_url":null,"source":{"id":"https://openalex.org/S4210224695","display_name":"Virtual Reality & Intelligent Hardware","issn_l":"2096-5796","issn":["2096-5796","2666-1209"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Virtual Reality & Intelligent Hardware","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.41210493445396423}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1982471090","https://openalex.org/W2102166818","https://openalex.org/W2133665775","https://openalex.org/W2914699769","https://openalex.org/W2952132648","https://openalex.org/W2997729188","https://openalex.org/W3096831136","https://openalex.org/W4382203549","https://openalex.org/W4391807605","https://openalex.org/W4393147998","https://openalex.org/W4393148505","https://openalex.org/W4403716358","https://openalex.org/W4405695475","https://openalex.org/W4407881938","https://openalex.org/W4409263204"],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"developments":[2],"of":[3,18,35,90,148,167],"artificial":[4],"intelligence":[5],"have":[6,48],"significantly":[7],"impacted":[8],"daily":[9],"life":[10],"and":[11,40,66,73,116,124,137,164],"content":[12],"production":[13],"modes.":[14],"In":[15,82,127],"the":[16,128,132],"field":[17],"video":[19,45,58,92,135,177],"generation,":[20,57],"researchers":[21],"are":[22],"now":[23],"exploring":[24],"this":[25,83],"emerging":[26],"technique":[27],"with":[28],"innovative":[29],"approaches,":[30],"aiming":[31],"to":[32,141,151,160,172],"produce":[33],"videos":[34],"higher":[36],"quality,":[37],"longer":[38],"duration,":[39],"greater":[41],"diversity.":[42],"Currently,":[43],"numerous":[44],"generation":[46,59,93],"algorithms":[47],"been":[49],"developed":[50],"using":[51],"different":[52,99,142],"architecture":[53],"designs.":[54],"Unlike":[55],"image":[56],"requires":[60],"maintaining":[61],"consistency":[62],"across":[63,98],"both":[64],"spatial":[65],"temporal":[67],"dimensions":[68],"while":[69],"ensuring":[70],"aesthetic":[71],"quality":[72],"dynamic":[74],"coherence,":[75],"making":[76],"it":[77],"a":[78,87,153,162],"more":[79,154],"challenging":[80],"task.":[81],"survey,":[84],"we":[85,130],"provide":[86,161],"systematic":[88],"review":[89,131],"existing":[91],"methods,":[94],"tracing":[95],"their":[96,108,118,139],"evolution":[97],"architectural":[100,122],"paradigms.":[101],"We":[102,144],"further":[103],"categorize":[104],"recent":[105],"models":[106,150],"by":[107],"control":[109],"conditions":[110],"(e.g.,":[111],"text-to-video,":[112],"image-to-video,":[113],"multi-modal":[114],"guidance)":[115],"summarize":[117],"unique":[119],"theoretical":[120],"foundations,":[121],"designs,":[123],"algorithmic":[125],"innovations.":[126],"meantime,":[129],"commonly":[133],"used":[134],"datasets":[136],"analyze":[138],"applicability":[140],"tasks.":[143],"also":[145],"present":[146],"evaluations":[147],"representative":[149],"offer":[152],"comprehensive":[155],"perspective.":[156],"Our":[157],"goal":[158],"is":[159],"clear":[163],"concise":[165],"overview":[166],"these":[168],"algorithms,":[169],"offering":[170],"insights":[171],"support":[173],"future":[174],"breakthroughs":[175],"in":[176],"generation.":[178]},"counts_by_year":[],"updated_date":"2026-05-17T08:19:37.847499","created_date":"2026-05-15T00:00:00"}