{"id":"https://openalex.org/W4413146740","doi":"https://doi.org/10.1109/cvpr52734.2025.01651","title":"4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion","display_name":"4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413146740","doi":"https://doi.org/10.1109/cvpr52734.2025.01651"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100669680","display_name":"Chaoyang Wang","orcid":"https://orcid.org/0000-0003-1750-5825"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaoyang Wang","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111226619","display_name":"Peiye Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peiye Zhuang","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101898499","display_name":"Tuan Ngo","orcid":"https://orcid.org/0000-0002-9831-8580"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuan Duc Ngo","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052645912","display_name":"Willi Menapace","orcid":"https://orcid.org/0000-0002-0715-9300"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Willi Menapace","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021757527","display_name":"Aliaksandr Siarohin","orcid":"https://orcid.org/0000-0001-9252-1775"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aliaksandr Siarohin","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031741585","display_name":"Michael Vasilkovsky","orcid":"https://orcid.org/0009-0007-4257-1636"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Vasilkovsky","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028188014","display_name":"Ivan Skorokhodov","orcid":"https://orcid.org/0000-0002-7611-9310"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Skorokhodov","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058028206","display_name":"Sergey Tulyakov","orcid":"https://orcid.org/0000-0003-3465-1592"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Tulyakov","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059559749","display_name":"Peter Wonka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Wonka","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026492424","display_name":"Hsin-Ying Lee","orcid":"https://orcid.org/0000-0003-2442-0117"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsin-Ying Lee","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6747,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.95200861,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"17723","last_page":"17732"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9871000051498413,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9871000051498413,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9761000275611877,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9646999835968018,"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":0.7368463277816772},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5125424861907959},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42790746688842773},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4260757863521576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3921624720096588},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.38427066802978516},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05394449830055237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368463277816772},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5125424861907959},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42790746688842773},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4260757863521576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3921624720096588},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.38427066802978516},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05394449830055237},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,43,80],"propose":[1,44,81],"4Real-Video,":[2],"a":[3,12,45,70],"novel":[4,46],"framework":[5],"for":[6],"generating":[7],"4D":[8],"videos,":[9],"organized":[10],"as":[11],"grid":[13],"of":[14,84],"video":[15],"frames":[16,29,38],"with":[17],"both":[18],"time":[19],"and":[20,56,114,116,119,125],"viewpoint":[21,52,120],"axes.":[22],"In":[23],"this":[24],"grid,":[25],"each":[26,35,66],"row":[27],"contains":[28,37],"sharing":[30],"the":[31,40,57,76,85],"same":[32,41],"timestep,":[33],"while":[34],"column":[36],"from":[39],"viewpoint.":[42],"two-stream":[47],"architecture.":[48],"One":[49],"stream":[50,59],"performs":[51,60],"updates":[53,62],"on":[54,63],"columns,":[55],"other":[58],"temporal":[61,118],"rows.":[64],"After":[65],"diffusion":[67],"transformer":[68],"layer,":[69,87],"synchronization":[71,86],"layer":[72],"exchanges":[73],"information":[74],"between":[75],"two":[77,82],"token":[78],"streams.":[79],"implementations":[83],"using":[88],"either":[89],"hard":[90],"or":[91],"soft":[92],"synchronization.":[93],"This":[94],"feedforward":[95],"architecture":[96],"improves":[97],"upon":[98],"previous":[99],"work":[100],"in":[101],"three":[102],"ways:":[103],"higher":[104],"inference":[105],"speed,":[106],"enhanced":[107],"visual":[108],"quality":[109],"(measured":[110,122],"by":[111,123],"FVD,":[112],"CLIP,":[113],"VideoScore),":[115],"improved":[117],"consistency":[121],"VideoScore":[124],"Dust3R-Confidence).":[126]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
