{"id":"https://openalex.org/W7113901267","doi":"https://doi.org/10.1109/tcsvt.2025.3642772","title":"2 <sup>2</sup> DEditor: Zero-Shot Text-Driven Volumetric Video Editing With Spatiotemporal Consistency via Single 2D Diffusion","display_name":"2 <sup>2</sup> DEditor: Zero-Shot Text-Driven Volumetric Video Editing With Spatiotemporal Consistency via Single 2D Diffusion","publication_year":2025,"publication_date":"2025-12-10","ids":{"openalex":"https://openalex.org/W7113901267","doi":"https://doi.org/10.1109/tcsvt.2025.3642772"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3642772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3642772","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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":"Qiaowei Miao","orcid":"https://orcid.org/0000-0002-8538-0342"},"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":"Qiaowei Miao","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-8538-0342","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":null,"display_name":"Kehan Li","orcid":"https://orcid.org/0009-0002-5942-816X"},"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":"Kehan Li","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0009-0002-5942-816X","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":null,"display_name":"Yawei Luo","orcid":"https://orcid.org/0000-0002-7037-1806"},"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":"Yawei Luo","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-7037-1806","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":null,"display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"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":"Yi Yang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0512-880X","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":3,"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":0.50637588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"6991","last_page":"7004"},"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":0.569100022315979,"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":0.569100022315979,"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":0.07639999687671661,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05400000140070915,"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/video-editing","display_name":"Video editing","score":0.70169997215271},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5385000109672546},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5213000178337097},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5088000297546387},{"id":"https://openalex.org/keywords/computational-photography","display_name":"Computational photography","score":0.4860999882221222},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.45579999685287476},{"id":"https://openalex.org/keywords/spatial-coherence","display_name":"Spatial coherence","score":0.4366999864578247},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.4108999967575073},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.39579999446868896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8788999915122986},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.70169997215271},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5692999958992004},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5385000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.529699981212616},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5213000178337097},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.4860999882221222},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.45579999685287476},{"id":"https://openalex.org/C2985909886","wikidata":"https://www.wikidata.org/wiki/Q193147","display_name":"Spatial coherence","level":3,"score":0.4366999864578247},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.3483999967575073},{"id":"https://openalex.org/C108944566","wikidata":"https://www.wikidata.org/wiki/Q1524510","display_name":"Panning (audio)","level":4,"score":0.3197000026702881},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C84824328","wikidata":"https://www.wikidata.org/wiki/Q4633097","display_name":"2D to 3D conversion","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3642772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3642772","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1661763918","display_name":null,"funder_award_id":"62293554","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1999039755","display_name":null,"funder_award_id":"2023ZD0121300","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G5586867142","display_name":null,"funder_award_id":"U2336212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Volumetric":[0],"video":[1,63,164,191],"represents":[2],"4D":[3],"(<italic":[4],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[5,57],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i.e</i>.,":[6],"dynamic":[7,49,156],"3D)":[8],"scenes":[9],"captured":[10],"from":[11],"multiple":[12],"viewpoints,":[13],"offering":[14],"rich":[15],"spatial":[16,110],"and":[17,31,48,89,118,146,151,176,183],"temporal":[18],"information":[19],"for":[20,28,115,188],"immersive":[21],"applications.":[22],"Despite":[23],"advances":[24],"in":[25,39,93],"diffusion-based":[26],"editing":[27,64,141,172],"images,":[29],"videos,":[30],"3D":[32],"objects,":[33],"achieving":[34],"precise,":[35],"spatiotemporally":[36],"coherent":[37,155],"edits":[38,126],"volumetric":[40,62,163,190],"videos":[41],"remains":[42],"challenging":[43],"due":[44],"to":[45,108,123],"complex":[46],"geometry":[47],"motion.":[50],"In":[51],"this":[52],"work,":[53],"we":[54,137],"propose":[55],"2<sup":[56],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>DEditor,":[58],"a":[59,71,139,185],"novel":[60],"zero-shot":[61,181],"framework":[65],"that":[66,167],"enforces":[67],"temporal-spatial":[68],"coherence":[69],"using":[70],"single":[72],"2D":[73],"diffusion":[74],"model.":[75],"A":[76],"key":[77],"component,":[78],"Spatiotemporal":[79],"Consistent":[80],"Null-Text":[81],"Optimization":[82],"(SCNO),":[83],"jointly":[84],"models":[85],"continuity":[86],"across":[87],"viewpoints":[88],"timestamps,":[90],"mitigating":[91],"inconsistencies":[92],"multi-frame":[94],"editing.":[95,192],"To":[96],"further":[97],"enhance":[98],"fidelity,":[99,175],"the":[100,131],"Source-Attention-Guided":[101],"Editing":[102],"(SAGE)":[103],"module":[104],"leverages":[105],"self-attention":[106],"maps":[107,114],"preserve":[109],"structures,":[111],"reuses":[112],"cross-attention":[113],"semantic":[116,174],"consistency,":[117,178],"aggregates":[119],"multi-layer":[120],"source":[121],"attention":[122],"prevent":[124],"unintended":[125],"when":[127],"target":[128],"objects":[129],"exit":[130],"scene.":[132],"Building":[133],"upon":[134],"these":[135],"components,":[136],"develop":[138],"round-by-round":[140],"pipeline,":[142],"enabling":[143],"diverse":[144],"local":[145],"global":[147],"modifications\u2014including":[148],"semantic,":[149],"stylistic,":[150],"attribute-based":[152],"adjustments\u2014while":[153],"maintaining":[154],"scene":[157],"structure.":[158],"Extensive":[159],"experiments":[160],"on":[161],"multi-view":[162],"datasets":[165],"demonstrate":[166],"our":[168],"approach":[169],"significantly":[170],"improves":[171],"precision,":[173],"spatiotemporal":[177],"outperforming":[179],"state-of-the-art":[180],"methods":[182],"establishing":[184],"new":[186],"benchmark":[187],"high-fidelity":[189]},"counts_by_year":[],"updated_date":"2026-05-08T13:12:06.581006","created_date":"2025-12-11T00:00:00"}