{"id":"https://openalex.org/W4408352304","doi":"https://doi.org/10.1109/icassp49660.2025.10889997","title":"EasyControl: Adding Control to Video Diffusion for Controllable Video Generation and Interpolation","display_name":"EasyControl: Adding Control to Video Diffusion for Controllable Video Generation and Interpolation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352304","doi":"https://doi.org/10.1109/icassp49660.2025.10889997"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100390469","display_name":"Cong Wang","orcid":"https://orcid.org/0000-0002-2863-0309"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Wang","raw_affiliation_strings":["Sun Yat-sen University at Shenzhen,School of Intelligent Engineering,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University at Shenzhen,School of Intelligent Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110919218","display_name":"Jiaxi Gu","orcid":"https://orcid.org/0000-0001-7732-5151"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxi Gu","raw_affiliation_strings":["Noah’ark Lab Huawei,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah’ark Lab Huawei,Shanghai,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043898209","display_name":"Panwen Hu","orcid":"https://orcid.org/0000-0001-6183-6598"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Panwen Hu","raw_affiliation_strings":["The Chinese University of Hong Kong at Shenzhen,School of Science and Engineering,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong at Shenzhen,School of Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101961088","display_name":"Xiao Dong","orcid":"https://orcid.org/0000-0001-9519-612X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Dong","raw_affiliation_strings":["Sun Yat-sen University at Zhuhai,School of Intelligent Engineering,Zhuhai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University at Zhuhai,School of Intelligent Engineering,Zhuhai,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021895690","display_name":"Yuanfan Guo","orcid":"https://orcid.org/0000-0002-5835-8545"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanfan Guo","raw_affiliation_strings":["Noah’ark Lab Huawei,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah’ark Lab Huawei,Shanghai,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102619815","display_name":"Hang Xu","orcid":"https://orcid.org/0009-0006-0421-0576"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Xu","raw_affiliation_strings":["Noah’ark Lab Huawei,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah’ark Lab Huawei,Shanghai,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Sun Yat-sen University at Shenzhen,School of Intelligent Engineering,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University at Shenzhen,School of Intelligent Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9907000064849854,"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":0.9907000064849854,"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":0.9769999980926514,"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":0.9646000266075134,"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/interpolation","display_name":"Interpolation (computer graphics)","score":0.6818643808364868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6669436693191528},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.43684422969818115},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.337218701839447},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.30698394775390625},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.06656280159950256}],"concepts":[{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6818643808364868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6669436693191528},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.43684422969818115},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.337218701839447},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30698394775390625},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.06656280159950256},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321160","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W845365781","https://openalex.org/W1592611919","https://openalex.org/W1901129140","https://openalex.org/W2133665775","https://openalex.org/W2425121537","https://openalex.org/W2473464331","https://openalex.org/W2604662340","https://openalex.org/W2605229288","https://openalex.org/W2769654144","https://openalex.org/W2955639361","https://openalex.org/W2962785568","https://openalex.org/W2963524571","https://openalex.org/W3031246127","https://openalex.org/W4226268312","https://openalex.org/W4285583561","https://openalex.org/W4312770027","https://openalex.org/W4318617422","https://openalex.org/W4379912396","https://openalex.org/W4385259380","https://openalex.org/W4385848606","https://openalex.org/W4386065764","https://openalex.org/W4386075779","https://openalex.org/W4388093548","https://openalex.org/W4388514904","https://openalex.org/W4389115686","https://openalex.org/W4390873054","https://openalex.org/W4390874580","https://openalex.org/W4393149921","https://openalex.org/W4402727587","https://openalex.org/W4402952315","https://openalex.org/W4403844572","https://openalex.org/W6600983433","https://openalex.org/W6779823529","https://openalex.org/W6852368155","https://openalex.org/W6853785652","https://openalex.org/W6856401663"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0,110],"diffusion":[1,93],"model":[2,29,47,131],"is":[3,22,123],"widely":[4],"leveraged":[5],"for":[6,30,96],"either":[7],"controllable":[8,100],"video":[9,12,101,135],"generation":[10,102],"or":[11],"interpolation.":[13],"As":[14],"each":[15,174],"field":[16],"has":[17],"its":[18],"task-specific":[19],"problems,":[20,81,141],"it":[21],"difficult":[23],"to":[24,49,71,89,117,132,148],"merely":[25],"develop":[26],"a":[27,91,114,144],"single":[28],"completing":[31],"both":[32,97],"tasks":[33,98],"simultaneously.":[34],"Moreover,":[35],"most":[36],"existing":[37],"works":[38],"only":[39],"support":[40],"image":[41,66,76],"conditions":[42],"and":[43,103],"necessitate":[44],"redesigning":[45],"the":[46,65,68,72,87,119,134,150,170],"structure":[48],"accommodate":[50],"other":[51],"types":[52,107],"of":[53,75,99,108,153],"conditions.":[54,109],"Even":[55],"so,":[56],"they":[57],"still":[58],"face":[59],"frame":[60,139],"flickering":[61],"issues":[62],"when":[63],"using":[64],"as":[67],"condition":[69,115,120,155],"due":[70],"strong":[73],"alignment":[74],"pixels.":[77],"To":[78,137],"tackle":[79],"these":[80],"in":[82],"this":[83],"work,":[84],"we":[85,142],"are":[86],"first":[88],"propose":[90,143],"unified":[92],"framework,":[94],"EasyControl,":[95],"interpolation":[104],"with":[105],"different":[106],"proposed":[111],"EasyControl":[112],"introduces":[113],"adapter":[116],"extract":[118],"features,":[121],"which":[122],"then":[124],"injected":[125],"into":[126],"an":[127],"interchangeable":[128],"fundamental":[129],"text-to-video":[130],"guide":[133],"generation.":[136,159],"alleviate":[138],"flicker":[140],"module":[145],"named":[146],"VideoInit":[147],"integrate":[149],"low-frequency":[151],"band":[152],"input":[154],"images,":[156],"ensuring":[157],"smoother":[158],"Experimental":[160],"results":[161],"on":[162,173],"four":[163],"benchmarks":[164],"suggest":[165],"that":[166],"our":[167],"method":[168],"outperforms":[169],"previous":[171],"methods":[172],"task.":[175]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}