{"id":"https://openalex.org/W4415798697","doi":"https://doi.org/10.52202/079017-0488","title":"4Diffusion: Multi-view Video Diffusion Model for 4D Generation","display_name":"4Diffusion: Multi-view Video Diffusion Model for 4D Generation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415798697","doi":"https://doi.org/10.52202/079017-0488"},"language":"en","primary_location":{"id":"doi:10.52202/079017-0488","doi":"https://doi.org/10.52202/079017-0488","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0488","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.20674","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116016380","display_name":"Haiyu Zhang","orcid":"https://orcid.org/0009-0001-9035-6224","observed_orcids":["https://orcid.org/0009-0001-9035-6224"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haiyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100664515","display_name":"Xinyuan Chen","orcid":"https://orcid.org/0000-0003-2990-2801","observed_orcids":["https://orcid.org/0000-0003-2990-2801","https://orcid.org/0009-0006-8891-9514"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyuan Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100672233","display_name":"Yaohui Wang","orcid":"https://orcid.org/0009-0002-9487-6187","observed_orcids":["https://orcid.org/0009-0002-9487-6187"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaohui Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027234036","display_name":"Xihui Liu","orcid":"https://orcid.org/0000-0002-1791-8745","observed_orcids":["https://orcid.org/0000-0002-1791-8745","https://orcid.org/0000-0003-1831-9952"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xihui Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115589096","display_name":"Yunhong Wang","orcid":"https://orcid.org/0000-0001-8001-2703","observed_orcids":["https://orcid.org/0000-0001-8001-2703"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunhong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101371688","display_name":"Yu Qiao","orcid":"https://orcid.org/0009-0000-3723-6496","observed_orcids":["https://orcid.org/0009-0000-3723-6496"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6925,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.93489314,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"15272","last_page":"15295"},"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":0.9980000257492065,"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":0.9980000257492065,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.00019999999494757503,"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/multi-view-video","display_name":"multi-view video","score":0.7179999947547913},{"id":"https://openalex.org/keywords/video-diffusion-models","display_name":"video diffusion models","score":0.8379999995231628},{"id":"https://openalex.org/keywords/video-to-video-translation","display_name":"video-to-video translation","score":0.38499999046325684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45500001311302185},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.328000009059906},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3127000033855438},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3027999997138977},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.26330000162124634},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2402999997138977}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.52202/079017-0488","doi":"https://doi.org/10.52202/079017-0488","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0488","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.20674","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.20674","pdf_url":"https://arxiv.org/pdf/2405.20674","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:hub.hku.hk:10722/359205","doi":null,"is_oa":false,"landing_page_url":"https://hub.hku.hk/handle/10722/359205","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference_Paper"},{"id":"doi:10.48550/arxiv.2405.20674","doi":"https://doi.org/10.48550/arxiv.2405.20674","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.20674","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.20674","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.20674","pdf_url":"https://arxiv.org/pdf/2405.20674","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415795691","https://openalex.org/W4403705810","https://openalex.org/W4417045270","https://openalex.org/W4407719447","https://openalex.org/W6910578992","https://openalex.org/W6891800385","https://openalex.org/W6947913003","https://openalex.org/W4416975529","https://openalex.org/W4393967366","https://openalex.org/W4416982480"],"abstract_inverted_index":{"Current":[0],"4D":[1,49,59,139,160],"generation":[2,50,76],"methods":[3,18],"have":[4],"achieved":[5],"noteworthy":[6],"efficacy":[7],"with":[8],"the":[9,110,116,170,175],"aid":[10],"of":[11,115,177],"advanced":[12],"diffusion":[13,33,70,87,101,118,135,153],"generative":[14],"models.":[15],"However,":[16],"these":[17],"lack":[19],"multi-view":[20,74,91,133],"spatial-temporal":[21,92],"modeling":[22],"and":[23,40,107,112,173,182],"encounter":[24],"challenges":[25],"in":[26,36],"integrating":[27],"diverse":[28],"prior":[29],"knowledge":[30],"from":[31,61,151],"multiple":[32,152],"models,":[34,154],"resulting":[35],"inconsistent":[37],"temporal":[38,105],"appearance":[39,171],"flickers.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,121,163],"propose":[46,122],"a":[47,62,68,79,84,97],"novel":[48],"pipeline,":[51],"namely":[52],"4Diffusion,":[53],"aimed":[54],"at":[55],"generating":[56,157],"spatial-temporally":[57,158],"consistent":[58,159],"content":[60],"monocular":[63],"video.":[64],"We":[65],"first":[66],"design":[67],"unified":[69],"model":[71,88,102],"tailored":[72],"for":[73,156],"video":[75,134],"by":[77,142],"incorporating":[78],"learnable":[80],"motion":[81],"module":[82],"into":[83],"frozen":[85],"3D-aware":[86,117],"to":[89,137,147,168,193],"capture":[90],"correlations.":[93],"After":[94],"training":[95],"on":[96,131],"curated":[98],"dataset,":[99],"our":[100,132,187],"acquires":[103],"reasonable":[104],"consistency":[106,114],"inherently":[108],"preserves":[109],"generalizability":[111],"spatial":[113],"model.":[119],"Subsequently,":[120],"4D-aware":[123],"Score":[124],"Distillation":[125],"Sampling":[126],"loss,":[127],"which":[128],"is":[129],"based":[130],"model,":[136],"optimize":[138],"representation":[140],"parameterized":[141],"dynamic":[143,178],"NeRF.":[144,179],"This":[145],"aims":[146],"eliminate":[148],"discrepancies":[149],"arising":[150],"allowing":[155],"content.":[161],"Moreover,":[162],"devise":[164],"an":[165],"anchor":[166],"loss":[167],"enhance":[169],"details":[172],"facilitate":[174],"learning":[176],"Extensive":[180],"qualitative":[181],"quantitative":[183],"experiments":[184],"demonstrate":[185],"that":[186],"method":[188],"achieves":[189],"superior":[190],"performance":[191],"compared":[192],"previous":[194],"methods.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":3}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-11-03T00:00:00"}