{"id":"https://openalex.org/W7160311882","doi":"https://doi.org/10.1109/wacv61042.2026.00817","title":"SmoothDiffusion-VE: Real-time Generative Video Editing Using Adaptive Feature Cache","display_name":"SmoothDiffusion-VE: Real-time Generative Video Editing Using Adaptive Feature Cache","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160311882","doi":"https://doi.org/10.1109/wacv61042.2026.00817"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5103255285","display_name":"Mustafa Munir","orcid":"https://orcid.org/0000-0003-0068-4580"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mustafa Munir","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135335670","display_name":"Sophia Zalewski","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sophia Zalewski","raw_affiliation_strings":["NVIDIA Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101869563","display_name":"Shiqiu Liu","orcid":"https://orcid.org/0000-0002-1036-2756"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiqiu Liu","raw_affiliation_strings":["NVIDIA Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061578459","display_name":"David Tarjan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Tarjan","raw_affiliation_strings":["NVIDIA Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135361988","display_name":"Sushmitha Belede","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sushmitha Belede","raw_affiliation_strings":["NVIDIA Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027283935","display_name":"Anjul Patney","orcid":"https://orcid.org/0000-0002-4911-2674"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anjul Patney","raw_affiliation_strings":["NVIDIA Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036227385","display_name":"Radu M\u0103rculescu","orcid":"https://orcid.org/0000-0003-1826-7646"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radu Marculescu","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"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":0.69110991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8468","last_page":"8478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9635999798774719,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9635999798774719,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.007000000216066837,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.004699999932199717,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/feature","display_name":"Feature (linguistics)","score":0.5270000100135803},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.30660000443458557},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2718999981880188},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.2687000036239624},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.25769999623298645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5703999996185303},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3822000026702881},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.24729999899864197}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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":33,"referenced_works":["https://openalex.org/W1578285471","https://openalex.org/W1755205674","https://openalex.org/W2132725786","https://openalex.org/W2886787375","https://openalex.org/W2962785568","https://openalex.org/W2966792645","https://openalex.org/W3096831136","https://openalex.org/W3109908659","https://openalex.org/W3141117710","https://openalex.org/W3159481202","https://openalex.org/W4312497550","https://openalex.org/W4312623579","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W4385801014","https://openalex.org/W4386076378","https://openalex.org/W4386076458","https://openalex.org/W4386113271","https://openalex.org/W4389539288","https://openalex.org/W4390871980","https://openalex.org/W4390872556","https://openalex.org/W4390873054","https://openalex.org/W4402660110","https://openalex.org/W4402702984","https://openalex.org/W4402726956","https://openalex.org/W4402753790","https://openalex.org/W4402753907","https://openalex.org/W4403990754","https://openalex.org/W4404965447","https://openalex.org/W4409262531","https://openalex.org/W4415798209","https://openalex.org/W7133185348","https://openalex.org/W7160169232"],"related_works":[],"abstract_inverted_index":{"Video":[0],"editing":[1,44],"with":[2],"diffusion":[3],"models":[4],"presents":[5],"significant":[6,91],"challenges,":[7,38],"especially":[8],"under":[9],"real-time":[10],"constraints.":[11],"Current":[12],"methods":[13],"either":[14],"enhance":[15],"temporal":[16,33,48,100],"consistency":[17,49],"at":[18],"the":[19,67],"cost":[20],"of":[21],"slow":[22],"processing":[23,51],"or":[24],"rely":[25],"on":[26,71,107,127],"frame-by-frame":[27],"editing,":[28],"leading":[29],"to":[30,79,86,97],"flickering":[31],"and":[32,50,60,119,140,155],"artifacts.":[34],"To":[35],"address":[36],"both":[37],"we":[39],"propose":[40],"SmoothDiffusion-VE,":[41],"a":[42,80,133,141,150],"streaming-based":[43],"approach":[45],"that":[46],"improves":[47],"speed":[52],"through":[53],"our":[54],"proposed":[55],"Adaptive":[56],"Feature":[57],"Cache":[58],"(AFC)":[59],"motion-guided":[61,103],"attention.":[62],"The":[63],"AFC":[64],"dynamically":[65],"adjusts":[66],"caching":[68,96],"behavior":[69],"based":[70],"perceptual":[72],"similarity":[73],"(LPIPS)":[74],"between":[75],"frames,":[76],"i.e.,":[77],"shifting":[78],"mini-cache":[81],"mode":[82],"for":[83,153],"similar":[84],"frames":[85],"reduce":[87],"computational":[88],"load.":[89],"Conversely,":[90],"frame":[92],"changes":[93],"trigger":[94],"deeper":[95],"maintain":[98],"robust":[99],"coherence.":[101],"Our":[102],"attention":[104],"selectively":[105],"focuses":[106],"dynamic":[108],"regions":[109],"using":[110],"optical":[111],"flow,":[112],"reducing":[113],"unnecessary":[114],"computations":[115],"in":[116],"static":[117],"areas":[118],"accelerating":[120],"processing.":[121],"SmoothDiffusion-VE":[122],"can":[123],"run":[124],"28":[125],"FPS":[126],"one":[128],"RTX":[129],"4090":[130],"GPU,":[131],"achieving":[132],"1564\u00d7":[134],"speedup":[135,143],"over":[136,144],"Plug-and-Play":[137],"Diffusion":[138,145],"(PNP)":[139],"1916\u00d7":[142],"Motion":[146],"Transfer":[147],"(DMT),":[148],"delivering":[149],"powerful":[151],"solution":[152],"fast":[154],"consistent":[156],"video":[157],"editing.":[158]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}
