{"id":"https://openalex.org/W4415540095","doi":"https://doi.org/10.1145/3746027.3755133","title":"Scene123: One Prompt to 3D Scene Generation via Video-Assisted and Consistency-Enhanced MAE","display_name":"Scene123: One Prompt to 3D Scene Generation via Video-Assisted and Consistency-Enhanced MAE","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540095","doi":"https://doi.org/10.1145/3746027.3755133"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755133","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5066005048","display_name":"Yiying Yang","orcid":"https://orcid.org/0009-0003-2413-1398"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiying Yang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-2413-1398","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076278944","display_name":"Fukun Yin","orcid":"https://orcid.org/0000-0003-2623-1619"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fukun Yin","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China and Stepfun, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2623-1619","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China and Stepfun, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiayuan Fan","orcid":"https://orcid.org/0000-0002-4983-1353"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayuan Fan","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4983-1353","affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042545034","display_name":"Wanzhang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanzhang Li","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-9755-2421","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363100","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0002-9347-1367"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["ByteDance Inc., Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-9347-1367","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Santa Clara, California, USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003400275","display_name":"Gang Yu","orcid":"https://orcid.org/0000-0001-5570-2710"},"institutions":[{"id":"https://openalex.org/I4210140476","display_name":"Shanghai Zhaozhan Metal Materials","ror":"https://ror.org/03wtw1749","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210140476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Yu","raw_affiliation_strings":["StepFun, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5570-2710","affiliations":[{"raw_affiliation_string":"StepFun, Shanghai, China","institution_ids":["https://openalex.org/I4210140476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3615","last_page":"3624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9998999834060669,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6640999913215637},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.47029998898506165},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4542999863624573},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42980000376701355},{"id":"https://openalex.org/keywords/texture-synthesis","display_name":"Texture synthesis","score":0.39570000767707825},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.3702999949455261},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.35269999504089355},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763000130653381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7315000295639038},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6640999913215637},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.583299994468689},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4542999863624573},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.39570000767707825},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.35269999504089355},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.2815999984741211},{"id":"https://openalex.org/C23690007","wikidata":"https://www.wikidata.org/wiki/Q1411145","display_name":"Radiance","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755133","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1982471090","https://openalex.org/W2117539524","https://openalex.org/W2943864248","https://openalex.org/W2986615800","https://openalex.org/W3048510980","https://openalex.org/W3174458495","https://openalex.org/W3176368002","https://openalex.org/W3180199962","https://openalex.org/W3204789496","https://openalex.org/W4200150166","https://openalex.org/W4312234520","https://openalex.org/W4312453532","https://openalex.org/W4312708649","https://openalex.org/W4312933868","https://openalex.org/W4313154783","https://openalex.org/W4313156423","https://openalex.org/W4321488276","https://openalex.org/W4365420366","https://openalex.org/W4385318467","https://openalex.org/W4386071604","https://openalex.org/W4386071957","https://openalex.org/W4386083069","https://openalex.org/W4388623114","https://openalex.org/W4390190305","https://openalex.org/W4390874165","https://openalex.org/W4390874211","https://openalex.org/W4393154693"],"related_works":[],"abstract_inverted_index":{"As":[0],"Artificial":[1],"Intelligence":[2],"Generated":[3],"Content":[4],"(AIGC)":[5],"advances,":[6],"a":[7,41,45,74,81,114,152,173,201],"variety":[8],"of":[9,104,168],"methods":[10],"have":[11],"been":[12],"developed":[13],"to":[14,29,48,85,99,120,150,160],"generate":[15,195],"text,":[16],"images,":[17],"videos,":[18],"and":[19,67,88,165,197,206],"3D":[20,75],"shapes":[21],"from":[22,40,62,179,200],"single":[23,42,202],"or":[24],"multimodal":[25],"inputs,":[26],"contributing":[27],"efforts":[28],"emulate":[30],"human-like":[31],"cognitive":[32],"content":[33],"creation.":[34],"However,":[35],"generating":[36],"realistic":[37,196],"large-scale":[38],"scenes":[39,199],"input":[43,111,181],"presents":[44],"challenge":[46],"due":[47],"the":[49,102,110,125,130,135,147,163,180,184],"complexities":[50],"involved":[51],"in":[52,141],"ensuring":[53],"consistency":[54,103],"across":[55,107],"extrapolated":[56],"views":[57,149],"generated":[58,169],"by":[59],"models.":[60],"Benefiting":[61],"recent":[63],"video":[64,82,185],"generation":[65,77,83,186],"models":[66],"implicit":[68,91],"neural":[69,92,153],"representations,":[70],"we":[71,145,171],"propose":[72],"Scene123,":[73],"scene":[76],"model,":[78],"which":[79],"combines":[80],"framework":[84],"ensure":[86,101],"realism":[87],"diversity":[89],"with":[90,95,124],"fields":[93],"integrated":[94],"Masked":[96],"Autoencoders":[97],"(MAE)":[98],"effectively":[100],"unseen":[105],"areas":[106],"views.":[108],"Specifically,":[109],"image":[112,182],"(or":[113],"text-generated":[115],"image)":[116],"is":[117],"first":[118],"warped":[119],"simulate":[121],"adjacent":[122],"views,":[123,170],"invisible":[126],"regions":[127],"filled":[128],"using":[129],"consistency-enhanced":[131],"MAE":[132],"model.":[133,187],"Nonetheless,":[134],"synthesized":[136],"images":[137,177],"often":[138],"exhibit":[139],"inconsistencies":[140],"viewpoint":[142],"alignment,":[143],"thus":[144],"utilize":[146],"produced":[148],"optimize":[151],"radiance":[154],"field,":[155],"enhancing":[156],"geometric":[157],"consistency.":[158],"Moreover,":[159],"further":[161],"enhance":[162],"details":[164],"texture":[166],"fidelity":[167],"employ":[172],"GAN-based":[174],"Loss":[175],"against":[176],"derived":[178],"through":[183],"Extensive":[188],"experiments":[189],"demonstrate":[190],"that":[191,210],"our":[192,211],"method":[193],"can":[194],"consistent":[198],"prompt.":[203],"Both":[204],"qualitative":[205],"quantitative":[207],"results":[208],"indicate":[209],"approach":[212],"surpasses":[213],"existing":[214],"state-of-the-art":[215],"methods.":[216]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}