{"id":"https://openalex.org/W7117453211","doi":"https://doi.org/10.1109/dicta68720.2025.11302466","title":"Streaming Video Diffusion: Online Video Editing with Diffusion Models","display_name":"Streaming Video Diffusion: Online Video Editing with Diffusion Models","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7117453211","doi":"https://doi.org/10.1109/dicta68720.2025.11302466"},"language":null,"primary_location":{"id":"doi:10.1109/dicta68720.2025.11302466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","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/A5017636354","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0003-1800-8441"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Feng Chen","raw_affiliation_strings":["The University of Adelaide"],"affiliations":[{"raw_affiliation_string":"The University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076928390","display_name":"Bohan Zhuang","orcid":"https://orcid.org/0000-0002-0074-0303"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]},{"id":"https://openalex.org/I2801239119","display_name":"Australian Regenerative Medicine Institute","ror":"https://ror.org/02qa5kg76","country_code":"AU","type":"facility","lineage":["https://openalex.org/I2801037857","https://openalex.org/I2801239119","https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bohan Zhuang","raw_affiliation_strings":["Monash University"],"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I2801239119","https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104085728","display_name":"Qi Wu","orcid":"https://orcid.org/0009-0001-7744-7906"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["The University of Adelaide"],"affiliations":[{"raw_affiliation_string":"The University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017636354"],"corresponding_institution_ids":["https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65493241,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.632099986076355,"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":0.632099986076355,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.11020000278949738,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.0868000015616417,"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":0.8621000051498413},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.5960000157356262},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5889999866485596},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5716999769210815},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5400999784469604},{"id":"https://openalex.org/keywords/video-capture","display_name":"Video capture","score":0.5238999724388123},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.5131000280380249},{"id":"https://openalex.org/keywords/non-linear-editing-system","display_name":"Non-linear editing system","score":0.42480000853538513},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42329999804496765},{"id":"https://openalex.org/keywords/smacker-video","display_name":"Smacker video","score":0.42260000109672546}],"concepts":[{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.8621000051498413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8514000177383423},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.5960000157356262},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5716999769210815},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.5238999724388123},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.5131000280380249},{"id":"https://openalex.org/C137402728","wikidata":"https://www.wikidata.org/wiki/Q1330119","display_name":"Non-linear editing system","level":5,"score":0.42480000853538513},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.42260000109672546},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.387800008058548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C2988167200","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Online video","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.3727000057697296},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33570000529289246},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3260999917984009},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C2986160907","wikidata":"https://www.wikidata.org/wiki/Q220499","display_name":"Video streaming","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.30720001459121704},{"id":"https://openalex.org/C166142869","wikidata":"https://www.wikidata.org/wiki/Q60061622","display_name":"Video production","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.2824000120162964},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C87829876","wikidata":"https://www.wikidata.org/wiki/Q648877","display_name":"Post-production","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dicta68720.2025.11302466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","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":14,"referenced_works":["https://openalex.org/W2964110616","https://openalex.org/W3094502228","https://openalex.org/W3204588463","https://openalex.org/W4226289673","https://openalex.org/W4312299780","https://openalex.org/W4312933868","https://openalex.org/W4386076712","https://openalex.org/W4389665351","https://openalex.org/W4390871782","https://openalex.org/W4390871980","https://openalex.org/W4390872556","https://openalex.org/W4390873135","https://openalex.org/W4393148505","https://openalex.org/W4402727429"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,104,112,140,148],"novel":[3],"task":[4],"called":[5],"online":[6,32,45],"video":[7,23,33,60],"editing,":[8],"which":[9,73],"is":[10,35,85,108],"designed":[11],"to":[12,37,102],"edit":[13,132],"streaming":[14,43,120],"frames":[15,27],"while":[16],"maintaining":[17],"temporal":[18,55,78,123],"consistency.":[19],"Unlike":[20],"existing":[21],"offline":[22],"editing":[24,34,61,118],"assuming":[25],"all":[26],"are":[28],"pre-established":[29],"and":[30,44,57,84,117],"accessible,":[31],"tailored":[36],"real-life":[38],"applications":[39],"such":[40],"as":[41],"live":[42],"chat,":[46],"requiring":[47],"(1)":[48],"fast":[49],"continual":[50],"step":[51],"inference,":[52],"(2)":[53],"long-term":[54],"modeling,":[56],"(3)":[58],"zero-shot":[59],"capability.":[62],"To":[63],"solve":[64],"these":[65],"issues,":[66],"we":[67],"propose":[68],"Streaming":[69],"Video":[70],"Diffusion":[71,83],"(SVDiff),":[72],"incorporates":[74],"the":[75,88],"compact":[76],"spatial-aware":[77],"recurrence":[79],"into":[80],"off-the-shelf":[81],"Stable":[82],"trained":[86],"with":[87,122,136],"segment-level":[89],"scheme":[90],"on":[91],"large-scale":[92],"long":[93],"videos.":[94],"This":[95],"simple":[96],"yet":[97],"effective":[98],"setup":[99],"allows":[100],"us":[101],"obtain":[103],"single":[105],"model":[106,130],"that":[107,128],"capable":[109],"of":[110,115,144,150],"executing":[111],"broad":[113],"range":[114],"videos":[116,135],"each":[119],"frame":[121],"coherence.":[124],"Our":[125],"experiments":[126],"indicate":[127],"our":[129],"can":[131],"long,":[133],"high-quality":[134],"remarkable":[137],"results,":[138],"achieving":[139],"real-time":[141],"inference":[142],"speed":[143],"15.2":[145],"FPS":[146],"at":[147],"resolution":[149],"<tex":[151],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[152],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$512":[153],"\\times":[154],"512$</tex>.":[155]},"counts_by_year":[],"updated_date":"2025-12-30T23:08:21.542490","created_date":"2025-12-29T00:00:00"}
