{"id":"https://openalex.org/W4401905945","doi":"https://doi.org/10.1109/tpami.2024.3450630","title":"Fast-Vid2Vid++: Spatial-Temporal Distillation for Real-Time Video-to-Video Synthesis","display_name":"Fast-Vid2Vid++: Spatial-Temporal Distillation for Real-Time Video-to-Video Synthesis","publication_year":2024,"publication_date":"2024-08-27","ids":{"openalex":"https://openalex.org/W4401905945","doi":"https://doi.org/10.1109/tpami.2024.3450630","pmid":"https://pubmed.ncbi.nlm.nih.gov/39190514"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3450630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3450630","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5039105857","display_name":"Long Zhuo","orcid":"https://orcid.org/0000-0003-1507-3360"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Zhuo","raw_affiliation_strings":["Shanghai AI Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1507-3360","affiliations":[{"raw_affiliation_string":"Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028380963","display_name":"Guangcong Wang","orcid":"https://orcid.org/0000-0002-6627-814X"},"institutions":[{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":null,"type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangcong Wang","raw_affiliation_strings":["Great Bay University, Dongguan, China"],"raw_orcid":"https://orcid.org/0000-0002-6627-814X","affiliations":[{"raw_affiliation_string":"Great Bay University, Dongguan, China","institution_ids":["https://openalex.org/I4396570619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054589909","display_name":"Shikai Li","orcid":"https://orcid.org/0009-0002-3947-2550"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikai Li","raw_affiliation_strings":["Shanghai AI Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000896822","display_name":"Wayne Wu","orcid":"https://orcid.org/0000-0002-1364-8151"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wayne Wu","raw_affiliation_strings":["Shanghai AI Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406050","display_name":"Ziwei Liu","orcid":"https://orcid.org/0000-0002-4220-5958"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziwei Liu","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4220-5958","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1514,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77699996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"46","issue":"12","first_page":"10732","last_page":"10747"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9959999918937683,"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":0.9959999918937683,"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":0.9908999800682068,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.7044509053230286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6676062345504761},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6435813307762146},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.429270476102829},{"id":"https://openalex.org/keywords/video-recording","display_name":"Video recording","score":0.4234336018562317},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3756033778190613},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3469541072845459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7044509053230286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6676062345504761},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6435813307762146},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.429270476102829},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.4234336018562317},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3756033778190613},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3469541072845459}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3450630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3450630","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39190514","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39190514","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2014506555","https://openalex.org/W2126897420","https://openalex.org/W2146395539","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2495425901","https://openalex.org/W2543539599","https://openalex.org/W2559085405","https://openalex.org/W2561238782","https://openalex.org/W2739879705","https://openalex.org/W2790491154","https://openalex.org/W2794857359","https://openalex.org/W2798170643","https://openalex.org/W2798691622","https://openalex.org/W2808168148","https://openalex.org/W2902437806","https://openalex.org/W2912851681","https://openalex.org/W2936864631","https://openalex.org/W2962851801","https://openalex.org/W2962927175","https://openalex.org/W2962965870","https://openalex.org/W2963363373","https://openalex.org/W2963524571","https://openalex.org/W2963592434","https://openalex.org/W2963674932","https://openalex.org/W2963800363","https://openalex.org/W2963876278","https://openalex.org/W2964005298","https://openalex.org/W2970400386","https://openalex.org/W2982083293","https://openalex.org/W2984529706","https://openalex.org/W2989221291","https://openalex.org/W2996880115","https://openalex.org/W2997005628","https://openalex.org/W2997563695","https://openalex.org/W3035147638","https://openalex.org/W3035170495","https://openalex.org/W3035204081","https://openalex.org/W3035540643","https://openalex.org/W3094786017","https://openalex.org/W3104263540","https://openalex.org/W3110422536","https://openalex.org/W3152912388","https://openalex.org/W3162366763","https://openalex.org/W3166466426","https://openalex.org/W3170343852","https://openalex.org/W3171287051","https://openalex.org/W3173562028","https://openalex.org/W3174256730","https://openalex.org/W3177640626","https://openalex.org/W3178284600","https://openalex.org/W3192083819","https://openalex.org/W3192333284","https://openalex.org/W3193053164","https://openalex.org/W3209554182","https://openalex.org/W4286611273","https://openalex.org/W4287728236","https://openalex.org/W4288088427","https://openalex.org/W4289792721","https://openalex.org/W4293390340","https://openalex.org/W4313026781","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6638632666","https://openalex.org/W6691815588","https://openalex.org/W6723181079","https://openalex.org/W6726275242","https://openalex.org/W6730179637","https://openalex.org/W6743188669","https://openalex.org/W6753914649","https://openalex.org/W6756789066","https://openalex.org/W6758552741","https://openalex.org/W6761540984","https://openalex.org/W6765779288","https://openalex.org/W6767264202","https://openalex.org/W6769148693","https://openalex.org/W6772524659","https://openalex.org/W6779487836","https://openalex.org/W6794010894"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2775347418","https://openalex.org/W2779427294","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W2324379218","https://openalex.org/W2005752236","https://openalex.org/W2205749934","https://openalex.org/W2032666489","https://openalex.org/W2730316057"],"abstract_inverted_index":{"Video-to-Video":[0],"synthesis":[1],"(Vid2Vid)":[2],"gains":[3],"remarkable":[4],"performance":[5,257],"in":[6,192],"generating":[7],"a":[8,12,109,255,267],"photo-realistic":[9],"video":[10,102,206],"from":[11,184],"sequence":[13],"of":[14,54,79,89,100,121,129,176,202,258],"semantic":[15],"maps,":[16],"such":[17],"as":[18],"segmentation,":[19],"sketch":[20],"and":[21,33,125,135,149,157,167,180,194,205,242,261],"pose.":[22],"However,":[23],"this":[24,105],"pipeline":[25],"is":[26,94],"heavily":[27],"limited":[28],"to":[29,39,86,145,153,188,208],"high":[30],"computational":[31,155,264],"cost":[32,265],"long":[34],"inference":[35,248],"latency,":[36],"mainly":[37,69],"attributed":[38],"two":[40],"essential":[41],"factors:":[42],"1)":[43],"network":[44,65,73,124,187,191],"architecture":[45],"parameters,":[46],"2)":[47],"sequential":[48,81],"data":[49,82,127,164,229],"stream.":[50,83,230],"Recently,":[51],"the":[52,77,80,87,98,101,122,126,139,163,169,174,177,181,185,189,199,203,209,213,227],"parameters":[53],"image-based":[55,92],"generative":[56,130],"models":[57,131],"have":[58],"been":[59],"significantly":[60],"reduced":[61],"via":[62],"more":[63],"efficient":[64],"architectures.":[66],"Existing":[67],"methods":[68],"focus":[70],"on":[71,118,132,266],"slimming":[72],"architectures":[74],"but":[75],"ignore":[76],"size":[78],"Moreover,":[84],"due":[85],"lack":[88],"temporal":[90,170],"coherence,":[91],"compression":[93,99,113],"not":[95],"sufficient":[96],"for":[97],"task.":[103],"In":[104],"paper,":[106],"we":[107,161],"present":[108],"spatial-temporal":[110,215],"hybrid":[111,216],"distillation":[112,120,218],"framework,":[114],"Fast-Vid2Vid++,":[115],"which":[116],"focuses":[117],"knowledge":[119,152,175,217],"teacher":[123,186],"stream":[128,165],"both":[133],"space":[134],"time.":[136],"Fast-Vid2Vid++":[137,232,253],"makes":[138],"first":[140],"attempt":[141],"at":[142],"time":[143,150],"dimension":[144],"transfer":[146,198],"hierarchical":[147,178],"features":[148,179,204],"coherence":[151],"reduce":[154,168],"resources":[156],"accelerate":[158],"inference.":[159],"Specifically,":[160],"compress":[162],"spatially":[166],"redundancy.":[171],"We":[172,197],"distill":[173],"final":[182],"response":[183],"student":[190,210],"high-resolution":[193,224],"full-time":[195],"domains.":[196],"long-term":[200],"dependencies":[201],"frames":[207,235],"model.":[211],"After":[212],"proposed":[214],"(Spatial-Temporal-HKD),":[219],"our":[220],"model":[221],"can":[222],"synthesize":[223],"key-frames":[225],"using":[226],"low-resolution":[228],"Finally,":[231],"interpolates":[233],"intermediate":[234],"by":[236],"motion":[237],"compensation":[238],"with":[239,246],"slight":[240],"latency":[241],"generates":[243],"full-length":[244],"sequences":[245],"motion-aware":[247],"(MAI).":[249],"On":[250],"standard":[251],"benchmarks,":[252],"achieves":[254],"real-time":[256],"30-59":[259],"FPS":[260],"saves":[262],"28-35\u00d7":[263],"single":[268],"V100":[269],"GPU.":[270]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}