{"id":"https://openalex.org/W4404649744","doi":"https://doi.org/10.48550/arxiv.2411.13552","title":"REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents","display_name":"REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents","publication_year":2024,"publication_date":"2024-11-20","ids":{"openalex":"https://openalex.org/W4404649744","doi":"https://doi.org/10.48550/arxiv.2411.13552"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.13552","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.13552","pdf_url":"https://arxiv.org/pdf/2411.13552","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.13552","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100771413","display_name":"Rui Tian","orcid":"https://orcid.org/0000-0003-2570-4322"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tian, Rui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101456786","display_name":"Qi Dai","orcid":"https://orcid.org/0000-0002-4693-2968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101369681","display_name":"Jianmin Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao, Jianmin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102742709","display_name":"Kai Qiu","orcid":"https://orcid.org/0000-0003-2071-4425"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Kai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115604599","display_name":"Yifan Yang","orcid":"https://orcid.org/0000-0002-9867-143X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yifan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101437627","display_name":"Chong Luo","orcid":"https://orcid.org/0000-0003-0939-474X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Chong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026167547","display_name":"Zuxuan Wu","orcid":"https://orcid.org/0000-0002-8689-5807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zuxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Yu-Gang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100771413"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9994999766349792,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9994999766349792,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9957000017166138,"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":0.9954000115394592,"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-vision","display_name":"Computer vision","score":0.540831983089447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5051193833351135},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.44915029406547546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.447727233171463},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4450661838054657}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.540831983089447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5051193833351135},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.44915029406547546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.447727233171463},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4450661838054657}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.13552","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.13552","pdf_url":"https://arxiv.org/pdf/2411.13552","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.13552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.13552","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.13552","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.13552","pdf_url":"https://arxiv.org/pdf/2411.13552","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G472569701","display_name":null,"funder_award_id":"62032006","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"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404649744.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Commercial":[0],"video":[1,105,154,173],"generation":[2,106,113,126],"models":[3,102],"have":[4],"exhibited":[5],"realistic,":[6],"high-fidelity":[7],"results":[8],"but":[9],"are":[10],"still":[11],"restricted":[12],"to":[13,45,86],"limited":[14],"access.":[15],"One":[16],"crucial":[17],"obstacle":[18],"for":[19,103],"large-scale":[20],"applications":[21],"is":[22,157],"the":[23,93,128,148],"expensive":[24],"training":[25,149],"and":[26,69,150,167],"inference":[27,151],"cost.":[28],"In":[29],"this":[30,54],"paper,":[31],"we":[32,56,98,109],"argue":[33],"that":[34,61,134],"videos":[35,63],"contain":[36],"significantly":[37,146],"more":[38],"redundant":[39],"information":[40],"than":[41],"images,":[42],"allowing":[43],"them":[44,71],"be":[46],"encoded":[47],"with":[48,127],"very":[49],"few":[50],"motion":[51],"latents.":[52],"Towards":[53],"goal,":[55],"design":[57],"an":[58],"image-conditioned":[59],"VAE":[60],"projects":[62],"into":[64],"extremely":[65],"compressed":[66],"latent":[67],"space":[68],"decode":[70],"based":[72],"on":[73,178],"content":[74],"images.":[75],"This":[76],"magic":[77],"Reducio":[78],"charm":[79],"enables":[80],"64x":[81],"reduction":[82],"of":[83,153],"latents":[84],"compared":[85],"a":[87,111,117,170,179],"common":[88],"2D":[89],"VAE,":[90],"without":[91],"sacrificing":[92],"quality.":[94],"Building":[95],"upon":[96],"Reducio-VAE,":[97],"can":[99,168],"train":[100],"diffusion":[101],"high-resolution":[104],"efficiently.":[107],"Specifically,":[108],"adopt":[110],"two-stage":[112],"paradigm,":[114],"first":[115],"generating":[116],"condition":[118],"image":[119],"via":[120],"text-to-image":[121],"generation,":[122],"followed":[123],"by":[124],"text-image-to-video":[125],"proposed":[129],"Reducio-DiT.":[130],"Extensive":[131],"experiments":[132],"show":[133],"our":[135,144],"model":[136],"achieves":[137],"strong":[138],"performance":[139],"in":[140,159,165],"evaluation.":[141],"More":[142],"importantly,":[143],"method":[145],"boosts":[147],"efficiency":[152],"LDMs.":[155],"Reducio-DiT":[156],"trained":[158],"just":[160],"3.2K":[161],"A100":[162,181],"GPU":[163],"hours":[164],"total":[166],"generate":[169],"16-frame":[171],"1024$\\times$1024":[172],"clip":[174],"within":[175],"15.5":[176],"seconds":[177],"single":[180],"GPU.":[182],"Code":[183],"released":[184],"at":[185],"https://github.com/microsoft/Reducio-VAE":[186],".":[187]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2024-11-24T00:00:00"}
