{"id":"https://openalex.org/W4413147690","doi":"https://doi.org/10.1109/cvpr52734.2025.00683","title":"Consistent and Controllable Image Animation with Motion Diffusion Models","display_name":"Consistent and Controllable Image Animation with Motion Diffusion Models","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147690","doi":"https://doi.org/10.1109/cvpr52734.2025.00683"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5023346211","display_name":"Xin Ma","orcid":"https://orcid.org/0000-0001-9117-9787"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xin Ma","raw_affiliation_strings":["Monash University,Faculty of Information Technology,Department of Data Science &amp; AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Faculty of Information Technology,Department of Data Science &amp; AI","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100672230","display_name":"Yaohui Wang","orcid":"https://orcid.org/0000-0003-0165-6573"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"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":"Yaohui Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gengyu Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gengyu Jia","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100664513","display_name":"Xinyuan Chen","orcid":"https://orcid.org/0000-0002-6127-9602"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"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":"Xinyuan Chen","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017857966","display_name":"Tien\u2010Tsin Wong","orcid":"https://orcid.org/0000-0002-7792-9307"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tien-Tsin Wong","raw_affiliation_strings":["Monash University,Faculty of Information Technology,Department of Data Science &amp; AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Faculty of Information Technology,Department of Data Science &amp; AI","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017943466","display_name":"Yuan-Fang Li","orcid":"https://orcid.org/0000-0003-4651-2821"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuan-Fang Li","raw_affiliation_strings":["Monash University,Faculty of Information Technology,Department of Data Science &amp; AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Faculty of Information Technology,Department of Data Science &amp; AI","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072508861","display_name":"Cunjian Chen","orcid":"https://orcid.org/0000-0002-2926-9762"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Cunjian Chen","raw_affiliation_strings":["Monash University,Faculty of Information Technology,Department of Data Science &amp; AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Faculty of Information Technology,Department of Data Science &amp; AI","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7288","last_page":"7298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9936000108718872,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9936000108718872,"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/T12290","display_name":"Human Motion and Animation","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9868000149726868,"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/animation","display_name":"Animation","score":0.7199923396110535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6799265146255493},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.6672279238700867},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.638077974319458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5310896635055542},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.527918815612793},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5227470397949219},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.4611056447029114},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10925155878067017}],"concepts":[{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7199923396110535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6799265146255493},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.6672279238700867},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.638077974319458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310896635055542},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.527918815612793},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5227470397949219},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.4611056447029114},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10925155878067017},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2121378366","https://openalex.org/W3112102641","https://openalex.org/W2013184069","https://openalex.org/W2989004599","https://openalex.org/W1976926596","https://openalex.org/W126583968","https://openalex.org/W2535923857","https://openalex.org/W2532377291","https://openalex.org/W2359575859","https://openalex.org/W2215755978"],"abstract_inverted_index":{"Diffusion":[0],"models":[1],"have":[2],"achieved":[3],"significant":[4],"progress":[5],"in":[6,32,79,93],"the":[7,23,33,68,84,89,94,107,122,147,156],"task":[8],"of":[9,61,70,109,121,124,151,173],"image":[10,46],"animation":[11,47],"due":[12],"to":[13,22,64,131],"their":[14],"powerful":[15],"generative":[16],"capabilities.":[17],"However,":[18],"preserving":[19],"appearance":[20,54],"consistency":[21,55],"static":[24],"input":[25],"image,":[26],"and":[27,56,136,149],"avoiding":[28],"abrupt":[29],"motion":[30,57,71,91,168],"change":[31],"generated":[34,95],"animation,":[35],"remains":[36],"challenging.":[37],"In":[38,155],"this":[39],"paper,":[40],"we":[41,86,111,158],"introduce":[42,112],"Cinemo,":[43],"a":[44,99,113],"novel":[45,100],"approach":[48],"that":[49],"aims":[50],"at":[51,182],"achieving":[52],"better":[53,119],"smoothness.":[58],"The":[59,177],"core":[60],"Cinemo":[62,130],"is":[63,180],"focus":[65],"on":[66],"learning":[67],"distribution":[69],"residuals,":[72],"rather":[73],"than":[74],"directly":[75],"predicting":[76],"frames":[77],"as":[78],"existing":[80],"diffusion":[81],"models.":[82],"During":[83],"inference,":[85],"further":[87],"mitigate":[88],"sudden":[90],"changes":[92],"video":[96,171],"by":[97],"introducing":[98],"DCT-based":[101],"noise":[102],"refinement":[103],"strategy.":[104],"To":[105],"counteract":[106],"over-smoothing":[108],"motion,":[110],"dynamics":[114],"degree":[115],"control":[116,120],"design":[117],"for":[118,167],"magnitude":[123],"motion.":[125],"Altogether,":[126],"these":[127],"strategies":[128],"enable":[129],"produce":[132],"highly":[133],"consistent,":[134],"smooth,":[135],"motion-controllable":[137],"results.":[138],"Extensive":[139],"experiments":[140],"compared":[141],"with":[142],"several":[143],"state-of-the-art":[144],"methods":[145],"demonstrate":[146,160],"effectiveness":[148],"superiority":[150],"our":[152,162],"proposed":[153],"approach.":[154],"end,":[157],"also":[159],"how":[161],"model":[163],"can":[164],"be":[165],"applied":[166],"transfer":[169],"or":[170],"editing":[172],"any":[174],"given":[175],"video.":[176],"project":[178],"page":[179],"available":[181],"https://maxin-cn.github.io/cinemo_project/.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
