{"id":"https://openalex.org/W4415538042","doi":"https://doi.org/10.1145/3746027.3755796","title":"S <sup>2</sup> -Edit3DV: Diffusion-Guided Style Meets Structure for Consistent Multi-View 3D Video Generation","display_name":"S <sup>2</sup> -Edit3DV: Diffusion-Guided Style Meets Structure for Consistent Multi-View 3D Video Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538042","doi":"https://doi.org/10.1145/3746027.3755796"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755796","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755796","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":"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":null,"display_name":"Yuqi Chen","orcid":"https://orcid.org/0009-0001-2140-400X"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"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":"Yuqi Chen","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0009-0001-2140-400X","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043803804","display_name":"Xiubo Liang","orcid":"https://orcid.org/0000-0002-4749-5552"},"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":"Xiubo Liang","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4749-5552","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111011565","display_name":"Yu Zhao","orcid":"https://orcid.org/0009-0000-7084-731X"},"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":"Yu Zhao","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-7084-731X","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038388306","display_name":"Hongzhi Wang","orcid":"https://orcid.org/0000-0001-6134-1309"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"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":"Hongzhi Wang","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0001-6134-1309","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100379826","display_name":"Weidong Geng","orcid":"https://orcid.org/0000-0002-2709-396X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Geng","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2709-396X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49414916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10583","last_page":"10592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9987999796867371,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9970999956130981,"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/stylized-fact","display_name":"Stylized fact","score":0.6362000107765198},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.5536999702453613},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.4747999906539917},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4413999915122986},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.4399999976158142},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.43560001254081726},{"id":"https://openalex.org/keywords/digital-watermarking","display_name":"Digital watermarking","score":0.3483999967575073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043000102043152},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.6362000107765198},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4747999906539917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4415000081062317},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38019999861717224},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.3483999967575073},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755796","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755796","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":26,"referenced_works":["https://openalex.org/W2603777577","https://openalex.org/W3216352822","https://openalex.org/W4200150166","https://openalex.org/W4385318467","https://openalex.org/W4386057725","https://openalex.org/W4386071957","https://openalex.org/W4386072096","https://openalex.org/W4386075604","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4389539682","https://openalex.org/W4390871980","https://openalex.org/W4390873054","https://openalex.org/W4390873135","https://openalex.org/W4390873195","https://openalex.org/W4390873915","https://openalex.org/W4390874580","https://openalex.org/W4393148800","https://openalex.org/W4400582115","https://openalex.org/W4402727736","https://openalex.org/W4402916440","https://openalex.org/W4403792256","https://openalex.org/W4403792452","https://openalex.org/W4404520200","https://openalex.org/W4404526243"],"related_works":[],"abstract_inverted_index":{"Consistently":[0],"stylizing":[1],"and":[2,20,36,104,117,129,152,168,176,184],"editing":[3,62,68,97],"3D":[4,60],"objects":[5,61],"from":[6,42],"multiple":[7],"viewpoints":[8],"is":[9],"crucial":[10],"for":[11,127,179],"immersive":[12],"applications":[13],"such":[14],"as":[15,63],"virtual":[16],"reality,":[17,19],"augmented":[18],"digital":[21],"entertainment.":[22],"Nevertheless,":[23],"existing":[24],"methods":[25],"frequently":[26],"face":[27],"significant":[28],"challenges,":[29],"including":[30],"inconsistent":[31],"textures,":[32],"pronounced":[33],"drifting":[34,91],"artifacts,":[35],"compromised":[37],"geometric":[38,166],"integrity":[39],"when":[40],"rendered":[41],"various":[43],"perspectives.":[44],"To":[45,99],"effectively":[46,133],"address":[47],"these":[48],"limitations,":[49],"we":[50,107],"introduce":[51],"S2-Edit3DV,":[52],"a":[53,64],"novel":[54],"diffusion-guided":[55],"framework":[56,159],"that":[57,156],"reframes":[58],"multi-view":[59,162],"temporally":[65],"coherent":[66],"video":[67],"problem.":[69],"By":[70],"exploiting":[71],"the":[72],"robust":[73,186],"single-view":[74],"generative":[75],"capabilities":[76],"of":[77],"SV3D,":[78],"our":[79,157],"approach":[80],"reliably":[81],"propagates":[82],"initial":[83],"style":[84,131],"edits":[85],"across":[86],"different":[87],"viewpoints,":[88],"substantially":[89],"mitigating":[90],"artifacts":[92],"prevalent":[93],"in":[94],"current":[95],"video-based":[96],"methods.":[98],"further":[100],"enhance":[101],"semantic":[102,125,135,171],"precision":[103],"structural":[105,148],"preservation,":[106],"propose":[108],"two":[109],"innovative":[110],"techniques:":[111],"Attention-based":[112],"Differential":[113],"Style":[114],"Injection":[115],"(ADSI)":[116],"Adaptive":[118],"Structural-aware":[119],"Plug-and-Play":[120],"(AS-PnP).":[121],"ADSI":[122],"utilizes":[123],"attention-driven":[124],"embeddings":[126],"adaptive":[128],"precise":[130],"injection,":[132],"reducing":[134],"hallucinations.":[136],"AS-PnP":[137],"strategically":[138],"modulates":[139],"stylized":[140],"latent":[141],"features,":[142],"balancing":[143],"artistic":[144],"expression":[145],"with":[146],"strict":[147],"coherence.":[149],"Comprehensive":[150],"evaluations":[151],"ablation":[153],"studies":[154],"demonstrate":[155],"proposed":[158],"significantly":[160],"enhances":[161],"consistency,":[163],"preserves":[164],"fine-grained":[165],"details,":[167],"ensures":[169],"accurate":[170],"alignment,":[172],"showcasing":[173],"superior":[174],"performance":[175],"practical":[177],"value":[178],"generating":[180],"high-quality,":[181],"creatively":[182],"stylized,":[183],"structurally":[185],"objects.":[187]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}
