{"id":"https://openalex.org/W4406610840","doi":"https://doi.org/10.1109/tcsvt.2025.3531390","title":"Spatio-Temporal Energy-Guided Diffusion Model for Zero-Shot Video Synthesis and Editing","display_name":"Spatio-Temporal Energy-Guided Diffusion Model for Zero-Shot Video Synthesis and Editing","publication_year":2025,"publication_date":"2025-01-20","ids":{"openalex":"https://openalex.org/W4406610840","doi":"https://doi.org/10.1109/tcsvt.2025.3531390"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3531390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3531390","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5022659405","display_name":"L. Yang","orcid":"https://orcid.org/0000-0003-1905-8053"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Yang","raw_affiliation_strings":["Institute of Medical Technology, Peking University Health Science Center, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1905-8053","affiliations":[{"raw_affiliation_string":"Institute of Medical Technology, Peking University Health Science Center, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yikai Zhao","orcid":"https://orcid.org/0009-0003-2166-4607"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yikai Zhao","raw_affiliation_strings":["Department of Computer Science, National University of Singapore, Cluny Road, Singapore","National University of Singapore, Singpore"],"raw_orcid":"https://orcid.org/0009-0003-2166-4607","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Cluny Road, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singpore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111136890","display_name":"Zhaochen Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaochen Yu","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China","Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-6720-3666","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bohan Zeng","orcid":"https://orcid.org/0009-0009-0999-6231"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohan Zeng","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China","Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-0999-6231","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020430648","display_name":"Minkai Xu","orcid":"https://orcid.org/0009-0007-9735-3767"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minkai Xu","raw_affiliation_strings":["Computer Science Department, Stanford University, Stanford, CA, USA","Stanford University, USA"],"raw_orcid":"https://orcid.org/0009-0007-9735-3767","affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080648149","display_name":"Shenda Hong","orcid":"https://orcid.org/0000-0001-7521-5127"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenda Hong","raw_affiliation_strings":["Institute of Medical Technology, Peking University Health Science Center, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7521-5127","affiliations":[{"raw_affiliation_string":"Institute of Medical Technology, Peking University Health Science Center, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062357883","display_name":"Bin Cui","orcid":"https://orcid.org/0000-0003-1681-4677"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Cui","raw_affiliation_strings":["Institute of Medical Technology, Peking University Health Science Center, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1681-4677","affiliations":[{"raw_affiliation_string":"Institute of Medical Technology, Peking University Health Science Center, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2358,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.94298513,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"35","issue":"6","first_page":"6034","last_page":"6046"},"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":0.9789999723434448,"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":0.9789999723434448,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.933899998664856,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9330999851226807,"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/computer-science","display_name":"Computer science","score":0.6829478144645691},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6473215818405151},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5089001655578613},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.43649280071258545},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43091779947280884},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.411201149225235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3846532106399536},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15334129333496094},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10931804776191711},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09986802935600281}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829478144645691},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6473215818405151},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5089001655578613},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.43649280071258545},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43091779947280884},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.411201149225235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3846532106399536},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15334129333496094},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10931804776191711},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09986802935600281},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3531390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3531390","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.6399999856948853,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G4431910321","display_name":null,"funder_award_id":"72125009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7209143175","display_name":null,"funder_award_id":"2022YFF1203001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7417188663","display_name":null,"funder_award_id":"2022YFF1203001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W2559085405","https://openalex.org/W2886934227","https://openalex.org/W2950689937","https://openalex.org/W2969985801","https://openalex.org/W3165405144","https://openalex.org/W3214985077","https://openalex.org/W4213207493","https://openalex.org/W4214774769","https://openalex.org/W4312122037","https://openalex.org/W4312872987","https://openalex.org/W4312933868","https://openalex.org/W4380905910","https://openalex.org/W4382457527","https://openalex.org/W4385245566","https://openalex.org/W4385801729","https://openalex.org/W4386071957","https://openalex.org/W4386072096","https://openalex.org/W4387195417","https://openalex.org/W4387805784","https://openalex.org/W4388469765","https://openalex.org/W4389539288","https://openalex.org/W4390871782","https://openalex.org/W4390871980","https://openalex.org/W4390872556","https://openalex.org/W4390872681","https://openalex.org/W4390872862","https://openalex.org/W4390873054","https://openalex.org/W4390873784","https://openalex.org/W4390874580","https://openalex.org/W4392151693","https://openalex.org/W4392824768","https://openalex.org/W4393148505","https://openalex.org/W4393148714","https://openalex.org/W4399665715","https://openalex.org/W4402727736","https://openalex.org/W4403716358","https://openalex.org/W4407351351","https://openalex.org/W6679045638","https://openalex.org/W6683825394","https://openalex.org/W6765775151","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6809885388","https://openalex.org/W6810793953","https://openalex.org/W6810940779","https://openalex.org/W6838327568","https://openalex.org/W6838639034","https://openalex.org/W6839916579","https://openalex.org/W6840155194","https://openalex.org/W6840815571","https://openalex.org/W6841366371","https://openalex.org/W6844305113","https://openalex.org/W6845281891","https://openalex.org/W6846820273","https://openalex.org/W6847090916","https://openalex.org/W6847119409","https://openalex.org/W6847223587","https://openalex.org/W6848729602","https://openalex.org/W6850630192","https://openalex.org/W6850636897","https://openalex.org/W6852368155","https://openalex.org/W6854463369","https://openalex.org/W6854944684","https://openalex.org/W6855605352","https://openalex.org/W6871579562","https://openalex.org/W6872866107","https://openalex.org/W6875921374"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Diffusion-based":[0],"generative":[1],"models":[2,17],"have":[3],"exhibited":[4],"considerable":[5],"success":[6],"in":[7,159],"conditional":[8],"video":[9,15,56,164],"synthesis":[10,57,165],"and":[11,58,119,126,143,156,166],"editing.":[12,167],"Nevertheless,":[13],"prevailing":[14],"diffusion":[16],"primarily":[18],"rely":[19],"on":[20],"conditioning":[21,117],"with":[22],"specific":[23,79],"input":[24,118],"modalities,":[25],"predominantly":[26],"text,":[27,147],"restricting":[28],"their":[29],"adaptability":[30],"to":[31,69,92],"alternative":[32],"modalities":[33],"without":[34,81],"necessitating":[35],"retraining":[36],"of":[37,141,162,175],"modality-specific":[38],"components.":[39],"In":[40],"this":[41],"work,":[42],"we":[43,64,98],"present":[44],"EnergyViD,":[45],"a":[46,100,138],"universal":[47],"spatio-temporal":[48],"Energy-guided":[49],"Video":[50],"Diffusion":[51],"model":[52],"designed":[53],"for":[54,84],"zero-shot":[55,163],"editing":[59],"across":[60,137],"diverse":[61],"conditions.":[62],"Specifically,":[63],"leverage":[65],"off-the-shelf":[66],"pre-trained":[67],"networks":[68],"construct":[70],"generic":[71],"energy":[72,107],"functions,":[73],"guiding":[74],"the":[75,82,111,116,120,160,176],"generation":[76],"process":[77],"under":[78],"conditions":[80,94],"need":[83],"retraining.":[85],"To":[86],"precisely":[87],"capture":[88],"temporal":[89],"dynamics":[90],"related":[91],"motion":[93,142],"(e.g.,":[95],"pose":[96],"sequences),":[97],"introduce":[99],"novel":[101],"kernel":[102],"Maximum":[103],"Mean":[104],"Discrepancy":[105],"(MMD)-based":[106],"function,":[108],"which":[109],"minimizes":[110],"global":[112],"distribution":[113],"discrepancy":[114],"between":[115],"generated":[121],"video.":[122],"Our":[123],"extensive":[124],"qualitative":[125],"quantitative":[127],"experiments":[128],"demonstrate":[129],"that":[130],"our":[131],"algorithm":[132],"consistently":[133],"produces":[134],"high-quality":[135],"results":[136],"wide":[139],"range":[140],"non-motion":[144],"conditions,":[145],"including":[146],"face":[148],"ID,":[149],"style,":[150],"poses,":[151],"depths,":[152],"sketches,":[153],"canny":[154],"edges,":[155],"segmentation":[157],"maps,":[158],"context":[161],"We":[168],"will":[169],"release":[170],"source":[171],"code":[172],"upon":[173],"acceptance":[174],"paper.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}