{"id":"https://openalex.org/W7168840203","doi":"https://doi.org/10.1145/3799902.3811114","title":"DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning","display_name":"DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7168840203","doi":"https://doi.org/10.1145/3799902.3811114"},"language":null,"primary_location":{"id":"doi:10.1145/3799902.3811114","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811114","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799902.3811114","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010072640","display_name":"Mingshuang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingshuang Luo","raw_affiliation_strings":["ByteDance, Beijing, China; Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4287-9055","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China; Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141041963","display_name":"Shuang Liang","orcid":"https://orcid.org/0009-0003-5966-352X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuang Liang","raw_affiliation_strings":["ByteDance, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-5966-352X","affiliations":[{"raw_affiliation_string":"ByteDance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140962832","display_name":"Zhengkun Rong","orcid":"https://orcid.org/0009-0001-8425-0618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengkun Rong","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8425-0618","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141044898","display_name":"Yuxuan Luo","orcid":"https://orcid.org/0009-0004-7973-1662"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Luo","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-7973-1662","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030742968","display_name":"Tianshu Hu","orcid":"https://orcid.org/0009-0004-9881-0673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianshu Hu","raw_affiliation_strings":["ByteDance, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-9881-0673","affiliations":[{"raw_affiliation_string":"ByteDance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002807265","display_name":"Ruibing Hou","orcid":"https://orcid.org/0000-0003-2480-6538"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibing Hou","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2480-6538","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037306106","display_name":"Hong Chang","orcid":"https://orcid.org/0000-0002-2668-0070"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Chang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2668-0070","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355406","display_name":"Yong Li","orcid":"https://orcid.org/0000-0002-6521-5921"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["School of Computer Science and Engineer, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6521-5921","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineer, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102603140","display_name":"Yuan Zhang","orcid":"https://orcid.org/0009-0008-4839-9520"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Zhang","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-4839-9520","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Mingyuan Gao","orcid":"https://orcid.org/0000-0003-0566-0780"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyuan Gao","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0566-0780","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]}],"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":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.7077000141143799},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6535999774932861},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5577999949455261},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4690999984741211},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44190001487731934},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.42250001430511475},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.42179998755455017},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4146000146865845},{"id":"https://openalex.org/keywords/character-animation","display_name":"Character animation","score":0.4120999872684479},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4050000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738000154495239},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7077000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7008000016212463},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6535999774932861},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5716000199317932},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5577999949455261},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4690999984741211},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.42250001430511475},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4146000146865845},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.4120999872684479},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4050000011920929},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3695000112056732},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3799902.3811114","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811114","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3799902.3811114","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811114","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2962785568","https://openalex.org/W2966421984","https://openalex.org/W3175471114","https://openalex.org/W3178284600","https://openalex.org/W4390190334","https://openalex.org/W4400585813","https://openalex.org/W4402660110","https://openalex.org/W4402704510","https://openalex.org/W4402727180","https://openalex.org/W4412587828","https://openalex.org/W4413145482","https://openalex.org/W4413145533","https://openalex.org/W4413146052","https://openalex.org/W4417125240","https://openalex.org/W7133196460","https://openalex.org/W7160121556"],"related_works":[],"abstract_inverted_index":{"Character":[0],"image":[1],"animation":[2,81],"aims":[3],"to":[4,15,37,68,120,158],"synthesize":[5],"high-fidelity":[6],"videos":[7],"by":[8,105,129],"transferring":[9],"motion":[10,32,44,85,110,172,193],"from":[11,26,155],"a":[12,16,38,48,79,95,113,140,152,182,186],"driving":[13],"sequence":[14],"static":[17],"reference":[18,107],"image.":[19],"Despite":[20],"recent":[21],"advancements,":[22],"existing":[23],"methods":[24],"suffer":[25],"two":[27],"fundamental":[28],"challenges:":[29],"(1)":[30],"suboptimal":[31],"injection":[33],"strategies":[34],"that":[35,83,145,198],"lead":[36],"trade-off":[39],"between":[40],"identity":[41,125],"preservation":[42],"and":[43,50,65,109,126,171,192,207],"consistency,":[45],"manifesting":[46],"as":[47,87],"\"see-saw\",":[49],"(2)":[51],"an":[52,88],"over-reliance":[53],"on":[54],"explicit":[55],"pose":[56],"priors":[57],"(e.g.,":[58],"skeletons),":[59],"which":[60],"inadequantely":[61],"capture":[62],"intricate":[63],"dynamics":[64,128],"hinder":[66],"generalization":[67,167],"arbitrary,":[69],"non-humanoid":[70],"characters.":[71],"To":[72,174],"address":[73],"these":[74],"challenges,":[75],"we":[76,99,138,178],"present":[77],"DreamActor-M2,":[78],"universal":[80],"framework":[82],"reimagines":[84],"conditioning":[86],"in-context":[89],"learning":[90],"problem.":[91],"Our":[92],"approach":[93],"follows":[94],"two-stage":[96],"paradigm.":[97],"First,":[98],"bridge":[100],"the":[101,118,131],"input":[102],"modality":[103],"gap":[104],"fusing":[106],"appearance":[108],"cues":[111],"into":[112],"unified":[114],"latent":[115],"space,":[116],"enabling":[117],"model":[119],"jointly":[121],"reason":[122],"about":[123],"spatial":[124],"temporal":[127],"leveraging":[130],"generative":[132],"prior":[133],"of":[134,189],"foundational":[135],"models.":[136],"Second,":[137],"introduce":[139,180],"self-bootstrapped":[141],"data":[142],"synthesis":[143],"pipeline":[144],"curates":[146],"pseudo":[147],"cross-identity":[148],"training":[149],"pairs,":[150],"facilitating":[151],"seamless":[153],"transition":[154],"pose-dependent":[156],"control":[157],"direct,":[159],"end-to-end":[160],"RGB-driven":[161],"animation.":[162],"This":[163],"strategy":[164],"significantly":[165],"enhances":[166],"across":[168],"diverse":[169],"characters":[170,190],"scenarios.":[173],"facilitate":[175],"comprehensive":[176],"evaluation,":[177],"further":[179],"AWBench,":[181],"versatile":[183],"benchmark":[184],"encompassing":[185],"wide":[187],"spectrum":[188],"categories":[191],"types.":[194],"Extensive":[195],"experiments":[196],"demonstrate":[197],"DreamActor-M2":[199],"achieves":[200],"state-of-the-art":[201],"performance,":[202],"delivering":[203],"superior":[204],"visual":[205],"fidelity":[206],"robust":[208],"cross-domain":[209],"generalization.":[210],"Project":[211],"Page:":[212],"https://grisoon.github.io/DreamActor-M2/":[213]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-07-17T00:00:00"}