{"id":"https://openalex.org/W7128728776","doi":"https://doi.org/10.1109/tpami.2026.3664227","title":"Consistent and Controllable Image Animation With Linear Motion Diffusion Transformers","display_name":"Consistent and Controllable Image Animation With Linear Motion Diffusion Transformers","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7128728776","doi":"https://doi.org/10.1109/tpami.2026.3664227","pmid":"https://pubmed.ncbi.nlm.nih.gov/41678482"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3664227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3664227","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/A5125770526","display_name":"Xin Ma","orcid":null},"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":["Department of Data Science & AI, Faculty of Information Technology, Monash University, Melbourne VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9389-9032","affiliations":[{"raw_affiliation_string":"Department of Data Science & AI, Faculty of Information Technology, Monash University, Melbourne VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051972265","display_name":"Yaohui Wang","orcid":"https://orcid.org/0009-0002-9487-6187"},"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":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaohui Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-9487-6187","affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125721979","display_name":"Genyun Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Genyun Jia","raw_affiliation_strings":["Hefei University of Technology, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-0513-138X","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125689947","display_name":"Xinyuan Chen","orcid":null},"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":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Chen","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5517-7255","affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111861371","display_name":"Tien-Tsin Wong","orcid":null},"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":["Department of Data Science & AI, Faculty of Information Technology, Monash University, Melbourne VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7792-9307","affiliations":[{"raw_affiliation_string":"Department of Data Science & AI, Faculty of Information Technology, Monash University, Melbourne VIC, Australia","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":["Department of Data Science & AI, Faculty of Information Technology, Monash University, Melbourne VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2926-9762","affiliations":[{"raw_affiliation_string":"Department of Data Science & AI, Faculty of Information Technology, Monash University, Melbourne VIC, Australia","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14363964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"7","first_page":"7436","last_page":"7450"},"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":0.8776999711990356,"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":0.8776999711990356,"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/T12290","display_name":"Human Motion and Animation","score":0.0722000002861023,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.008999999612569809,"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/animation","display_name":"Animation","score":0.6209999918937683},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4521999955177307},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.4456000030040741},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.40790000557899475},{"id":"https://openalex.org/keywords/motion-field","display_name":"Motion field","score":0.40310001373291016},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.3955000042915344},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.35199999809265137},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.34599998593330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682999968528748},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6568999886512756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6531999707221985},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6209999918937683},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C124774092","wikidata":"https://www.wikidata.org/wiki/Q6917782","display_name":"Motion field","level":3,"score":0.40310001373291016},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3955000042915344},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.35199999809265137},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.34599998593330383},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.33079999685287476},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.3179999887943268},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3102000057697296},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3664227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3664227","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:41678482","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41678482","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W2047491370","https://openalex.org/W2099447573","https://openalex.org/W2425121537","https://openalex.org/W2483471159","https://openalex.org/W2883861033","https://openalex.org/W2902266071","https://openalex.org/W2948978827","https://openalex.org/W2963091558","https://openalex.org/W2964245526","https://openalex.org/W2990375436","https://openalex.org/W3028959255","https://openalex.org/W3109908659","https://openalex.org/W3166255651","https://openalex.org/W3176504418","https://openalex.org/W3178284600","https://openalex.org/W3199125932","https://openalex.org/W4297697565","https://openalex.org/W4312694728","https://openalex.org/W4312933868","https://openalex.org/W4386065764","https://openalex.org/W4386065887","https://openalex.org/W4386071497","https://openalex.org/W4386071957","https://openalex.org/W4386113271","https://openalex.org/W4388979610","https://openalex.org/W4390872297","https://openalex.org/W4390872681","https://openalex.org/W4390872738","https://openalex.org/W4390873135","https://openalex.org/W4394625831","https://openalex.org/W4400580599","https://openalex.org/W4401807241","https://openalex.org/W4402660110","https://openalex.org/W4402702927","https://openalex.org/W4402704510","https://openalex.org/W4402715897","https://openalex.org/W4402727092","https://openalex.org/W4402727736","https://openalex.org/W4402876471","https://openalex.org/W4403003238","https://openalex.org/W4403844572","https://openalex.org/W4403906558","https://openalex.org/W4408351875","https://openalex.org/W4409367025","https://openalex.org/W4413144457","https://openalex.org/W4413144599","https://openalex.org/W4413145195","https://openalex.org/W4413145312","https://openalex.org/W4413145533","https://openalex.org/W4413145725","https://openalex.org/W4413145894","https://openalex.org/W4413146052","https://openalex.org/W4413146266","https://openalex.org/W4413146475","https://openalex.org/W4413146531","https://openalex.org/W4413147005","https://openalex.org/W4413147163","https://openalex.org/W4413147681","https://openalex.org/W4413147690","https://openalex.org/W4413147827","https://openalex.org/W4413156651","https://openalex.org/W4415796345","https://openalex.org/W7133185348"],"related_works":[],"abstract_inverted_index":{"Image":[0],"animation":[1,48,80],"has":[2,38],"seen":[3],"significant":[4],"progress,":[5],"driven":[6],"by":[7,166],"the":[8,46,60,65,183,201],"powerful":[9],"generative":[10],"capabilities":[11],"of":[12,68,185,203],"diffusion":[13,43,55],"models.":[14],"However,":[15],"maintaining":[16],"appearance":[17,96],"consistency":[18],"with":[19,42,118,194],"static":[20],"input":[21],"images":[22],"and":[23,98,151,175,191,210],"mitigating":[24],"abrupt":[25],"motion":[26,99,133,141,163,173,208],"transitions":[27],"in":[28,72,101,187,207],"generated":[29],"animations":[30,193],"remain":[31],"persistent":[32],"challenges.":[33],"While":[34],"text-to-video":[35,113],"(T2V)":[36],"generation":[37,128],"demonstrated":[39],"impressive":[40],"performance":[41],"transformer":[44],"models,":[45,56],"image":[47,79,102],"field":[49],"still":[50],"largely":[51],"relies":[52],"on":[53,139],"U-Net-based":[54],"which":[57],"lag":[58],"behind":[59],"latest":[61],"T2V":[62],"approaches.":[63],"Moreover,":[64],"quadratic":[66],"complexity":[67],"vanilla":[69,116],"self-attention":[70,117],"mechanisms":[71],"Transformers":[73],"imposes":[74],"heavy":[75],"computational":[76,124],"demands,":[77],"making":[78],"particularly":[81],"resource-intensive.":[82],"To":[83],"address":[84],"these":[85],"issues,":[86],"we":[87,199],"propose":[88],"MiraMo,":[89],"a":[90,167],"framework":[91],"designed":[92],"to":[93,122,160,171],"enhance":[94],"efficiency,":[95],"consistency,":[97],"smoothness":[100,174],"animation.":[103],"Specifically,":[104],"MiraMo":[105,186,204],"introduces":[106],"three":[107],"key":[108],"elements:":[109],"(1)":[110],"A":[111,131,153],"foundational":[112],"architecture":[114],"replacing":[115],"efficient":[119],"linear":[120],"attention":[121],"reduce":[123],"overhead":[125],"while":[126],"preserving":[127],"quality;":[129],"(2)":[130],"novel":[132],"residual":[134],"learning":[135],"paradigm":[136],"that":[137],"focuses":[138],"modeling":[140],"dynamics":[142,168],"rather":[143],"than":[144],"directly":[145],"predicting":[146],"frames,":[147],"improving":[148],"temporal":[149],"consistency;":[150],"(3)":[152],"DCT-based":[154],"noise":[155],"refinement":[156],"strategy":[157],"during":[158],"inference":[159,196],"suppress":[161],"sudden":[162],"artifacts,":[164],"complemented":[165],"control":[169],"module":[170],"balance":[172],"expressiveness.":[176],"Extensive":[177],"experiments":[178],"against":[179],"state-of-the-art":[180],"methods":[181],"validate":[182],"superiority":[184],"generating":[188],"consistent,":[189],"smooth,":[190],"controllable":[192],"accelerated":[195],"speed.":[197],"Additionally,":[198],"demonstrate":[200],"versatility":[202],"through":[205],"applications":[206],"transfer":[209],"video":[211],"editing":[212],"tasks.":[213]},"counts_by_year":[],"updated_date":"2026-06-07T06:13:29.825681","created_date":"2026-02-13T00:00:00"}