{"id":"https://openalex.org/W4390091523","doi":"https://doi.org/10.1109/iccv51701.2025.01150","title":"StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation","display_name":"StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4390091523","doi":"https://doi.org/10.1109/iccv51701.2025.01150"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.12491","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063768109","display_name":"Akio Kodaira","orcid":"https://orcid.org/0000-0003-4636-1904"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Akio Kodaira","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083914796","display_name":"Chenfeng Xu","orcid":"https://orcid.org/0000-0002-4941-6985"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenfeng Xu","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078246605","display_name":"Toshiki Hazama","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Toshiki Hazama","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058273811","display_name":"Takanori Yoshimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanori Yoshimoto","raw_affiliation_strings":["University of Tsukuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108705985","display_name":"Kohei Ohno","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kohei Ohno","raw_affiliation_strings":["International Christian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Christian University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093557660","display_name":"Shogo Mitsuhori","orcid":null},"institutions":[{"id":"https://openalex.org/I158123994","display_name":"Toyo University","ror":"https://ror.org/059d6yn51","country_code":"JP","type":"education","lineage":["https://openalex.org/I158123994"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shogo Mitsuhori","raw_affiliation_strings":["Toyo University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyo University","institution_ids":["https://openalex.org/I158123994"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113078414","display_name":"Soichi Sugano","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Soichi Sugano","raw_affiliation_strings":["Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104218437","display_name":"Hanying Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hanying Cho","raw_affiliation_strings":["Tohoku University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750264","display_name":"Zhijian Liu","orcid":"https://orcid.org/0000-0003-3632-9986"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Zhijian Liu","raw_affiliation_strings":["MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Masayoshi Tomizuka","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masayoshi Tomizuka","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kurt Keutzer","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt Keutzer","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5063768109"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":6.3909,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.96064746,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12371","last_page":"12380"},"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":0.9915000200271606,"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":0.9915000200271606,"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":0.9912999868392944,"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":0.9847999811172485,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8510911464691162},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6247966885566711},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.599183976650238},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5621288418769836},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5017750263214111},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.48515185713768005},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.447191059589386},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4291996955871582},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42872732877731323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3722798824310303},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.330200731754303},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.29557153582572937},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28674566745758057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510911464691162},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6247966885566711},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.599183976650238},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5621288418769836},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5017750263214111},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.48515185713768005},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.447191059589386},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4291996955871582},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42872732877731323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3722798824310303},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.330200731754303},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.29557153582572937},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28674566745758057},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2312.12491","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.12491","pdf_url":"https://arxiv.org/pdf/2312.12491","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2312.12491","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.12491","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.12491","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.12491","pdf_url":"https://arxiv.org/pdf/2312.12491","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309411","display_name":"University of California Berkeley","ror":"https://ror.org/01an7q238"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3046370962"],"abstract_inverted_index":{"We":[0],"introduce":[1,155],"StreamDiffusion,":[2],"a":[3,61,102,131,156],"real-time":[4,31],"diffusion":[5,13,114],"pipeline":[6,115],"designed":[7],"for":[8,106],"interactive":[9],"image":[10,23],"generation.":[11],"Existing":[12],"models":[14],"are":[15],"adept":[16],"at":[17,177],"creating":[18],"images":[19],"from":[20],"text":[21],"or":[22,150],"prompts,":[24],"yet":[25],"they":[26],"often":[27],"fall":[28],"short":[29],"in":[30,38],"interaction.":[32],"This":[33],"limitation":[34],"becomes":[35],"particularly":[36],"evident":[37],"scenarios":[39],"involving":[40],"continuous":[41],"input,":[42],"such":[43],"as":[44],"Metaverse,":[45],"live":[46],"video":[47],"streaming,":[48],"and":[49,82,85,97,199,239],"broadcasting,":[50],"where":[51],"high":[52,86],"throughput":[53,87],"is":[54],"imperative.":[55],"To":[56,89,124],"address":[57],"this,":[58],"we":[59,100,129,154],"present":[60],"novel":[62,103,132],"approach":[63,81],"that":[64,138],"transforms":[65],"the":[66,71,78,91,108,112,126,140,173,192,196,205,215,231],"original":[67],"sequential":[68,174],"denoising":[69,73,145,175,179],"into":[70],"batching":[72],"process.":[74,110],"Stream":[75,165],"Batch":[76,166],"eliminates":[77],"conventional":[79,193],"wait-and-interact":[80],"enables":[83],"fluid":[84],"streams.":[88],"handle":[90],"frequency":[92],"disparity":[93],"between":[94],"data":[95],"input":[96],"model":[98],"throughput,":[99],"design":[101],"input-output":[104],"queue":[105],"parallelizing":[107],"streaming":[109],"Moreover,":[111],"existing":[113,200],"uses":[116],"classifier-free":[117,134],"guidance(CFG),":[118],"which":[119],"requires":[120],"additional":[121],"U-Net":[122],"computation.":[123],"mitigate":[125],"redundant":[127],"computations,":[128],"propose":[130],"residual":[133],"guidance":[135],"(RCFG)":[136],"algorithm":[137],"reduces":[139,230],"number":[141],"of":[142,217],"negative":[143],"conditional":[144],"steps":[146],"to":[147,160,172,185,188],"only":[148],"one":[149,212,237,242],"even":[151],"zero.":[152],"Besides,":[153],"stochastic":[157],"similarity":[158],"filter(SSF)":[159],"optimize":[161],"power":[162],"consumption.":[163],"Our":[164],"achieves":[167],"around":[168],"1.5x":[169],"speedup":[170],"compared":[171],"method":[176],"different":[178],"levels.":[180],"The":[181],"proposed":[182,197,226],"RCFG":[183],"leads":[184],"speeds":[186],"up":[187],"2.05x":[189],"higher":[190],"than":[191],"CFG.":[194],"Combining":[195],"strategies":[198],"mature":[201],"acceleration":[202],"tools":[203],"makes":[204],"image-to-image":[206],"generation":[207],"achieve":[208],"up-to":[209],"91.07fps":[210],"on":[211,236,241],"RTX4090,":[213,243],"improving":[214],"throughputs":[216],"AutoPipline":[218],"developed":[219],"by":[220,234],"Diffusers":[221],"over":[222],"59.56x.":[223],"Furthermore,":[224],"our":[225],"StreamDiffusion":[227],"also":[228],"significantly":[229],"energy":[232],"consumption":[233],"2.39x":[235],"RTX3060":[238],"1.99x":[240],"respectively.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":6}],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}