{"id":"https://openalex.org/W4417125358","doi":"https://doi.org/10.1145/3757377.3763885","title":"AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models","display_name":"AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417125358","doi":"https://doi.org/10.1145/3757377.3763885"},"language":null,"primary_location":{"id":"doi:10.1145/3757377.3763885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-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/A5036583882","display_name":"Zehuan Huang","orcid":"https://orcid.org/0009-0002-1883-0777"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zehuan Huang","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100301042","display_name":"Haoran Feng","orcid":"https://orcid.org/0009-0001-0239-9137"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Feng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066898339","display_name":"Yang-Tian Sun","orcid":"https://orcid.org/0000-0001-6370-1603"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yang-Tian Sun","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102364152","display_name":"Yuan\u2013Chen Guo","orcid":"https://orcid.org/0000-0001-6164-8343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan-Chen Guo","raw_affiliation_strings":["VAST, Beijing, China"],"affiliations":[{"raw_affiliation_string":"VAST, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091525681","display_name":"Yan\u2010Pei Cao","orcid":"https://orcid.org/0000-0002-0416-4374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan-Pei Cao","raw_affiliation_strings":["VAST, Beijing, China"],"affiliations":[{"raw_affiliation_string":"VAST, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035443556","display_name":"Lu Sheng","orcid":"https://orcid.org/0000-0002-8525-9163"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Sheng","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036583882"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.2158,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85293086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.6287000179290771,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.6287000179290771,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.3084000051021576,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.026799999177455902,"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":0.6908000111579895},{"id":"https://openalex.org/keywords/polygon-mesh","display_name":"Polygon mesh","score":0.6897000074386597},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6751000285148621},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5698000192642212},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5170999765396118},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.48910000920295715},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.47049999237060547},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4050999879837036},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3725000023841858},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.3384000062942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282000184059143},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6919000148773193},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6908000111579895},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.6897000074386597},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6751000285148621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6053000092506409},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.541100025177002},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5170999765396118},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.48910000920295715},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.47049999237060547},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.3255000114440918},{"id":"https://openalex.org/C124774092","wikidata":"https://www.wikidata.org/wiki/Q6917782","display_name":"Motion field","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.3037000000476837},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C204366326","wikidata":"https://www.wikidata.org/wiki/Q3027650","display_name":"Deformation (meteorology)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C44710944","wikidata":"https://www.wikidata.org/wiki/Q1813564","display_name":"Skeletal animation","level":5,"score":0.2667999863624573},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.258899986743927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757377.3763885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W1999165127","https://openalex.org/W2483862638","https://openalex.org/W2971856312","https://openalex.org/W2982625143","https://openalex.org/W3153220274","https://openalex.org/W3180355996","https://openalex.org/W3214782054","https://openalex.org/W4250666038","https://openalex.org/W4297981470","https://openalex.org/W4312635677","https://openalex.org/W4312933868","https://openalex.org/W4313145975","https://openalex.org/W4386065848","https://openalex.org/W4386071957","https://openalex.org/W4386075660","https://openalex.org/W4386076288","https://openalex.org/W4388979610","https://openalex.org/W4390438128","https://openalex.org/W4390872297","https://openalex.org/W4390873550","https://openalex.org/W4391305822","https://openalex.org/W4393153655","https://openalex.org/W4393967366","https://openalex.org/W4399151919","https://openalex.org/W4399253088","https://openalex.org/W4402547109","https://openalex.org/W4402660110","https://openalex.org/W4402715856","https://openalex.org/W4402716105","https://openalex.org/W4402716158","https://openalex.org/W4402727067","https://openalex.org/W4402727501","https://openalex.org/W4402727915","https://openalex.org/W4402733584","https://openalex.org/W4403002917","https://openalex.org/W4403705810","https://openalex.org/W4404355690","https://openalex.org/W4405562807","https://openalex.org/W4406093125","https://openalex.org/W4409049129","https://openalex.org/W4412595426","https://openalex.org/W4413144387","https://openalex.org/W4415098792","https://openalex.org/W4415288226","https://openalex.org/W4415795691","https://openalex.org/W6910578992"],"related_works":[],"abstract_inverted_index":{"We":[0,87],"present":[1],"AnimaX,":[2],"a":[3,83,133,154],"feed-forward":[4],"3D":[5,53,65,120,159],"animation":[6,127],"framework":[7],"that":[8],"bridges":[9],"the":[10,18,52],"motion":[11,25,49,66,85,109,149],"priors":[12,107],"of":[13,21,137],"video":[14,100,106],"diffusion":[15,77],"models":[16],"with":[17,59],"controllable":[19],"structure":[20],"skeleton-based":[22],"animation.":[23,160],"Traditional":[24],"synthesis":[26],"methods":[27],"are":[28,117],"either":[29],"restricted":[30],"to":[31,51,95,108],"fixed":[32],"skeletal":[33],"topologies":[34],"or":[35],"require":[36],"costly":[37],"optimization":[38],"in":[39,147],"high-dimensional":[40],"deformation":[41],"spaces.":[42],"In":[43],"contrast,":[44],"AnimaX":[45,141],"effectively":[46,104],"transfers":[47],"video-based":[48],"knowledge":[50],"domain,":[54],"supporting":[55],"diverse":[56],"articulated":[57],"meshes":[58],"arbitrary":[60],"skeletons.":[61],"Our":[62],"method":[63],"represents":[64],"as":[67],"multi-view,":[68],"multi-frame":[69],"2D":[70],"pose":[71,102,115],"maps,":[72],"and":[73,82,92,101,123,151],"enables":[74],"joint":[75,121],"video-pose":[76],"conditioned":[78],"on":[79,132,145],"template":[80],"renderings":[81],"textual":[84],"prompt.":[86],"introduce":[88],"shared":[89],"positional":[90],"encodings":[91],"modality-aware":[93],"embeddings":[94],"ensure":[96],"spatial-temporal":[97],"alignment":[98],"between":[99],"sequences,":[103,140],"transferring":[105],"generation":[110],"task.":[111],"The":[112],"resulting":[113],"multi-view":[114],"sequences":[116],"triangulated":[118],"into":[119,125],"positions":[122],"converted":[124],"mesh":[126],"via":[128],"inverse":[129],"kinematics.":[130],"Trained":[131],"newly":[134],"curated":[135],"dataset":[136],"160,000":[138],"rigged":[139],"achieves":[142],"state-of-the-art":[143],"results":[144],"VBench":[146],"generalization,":[148],"fidelity,":[150],"efficiency,":[152],"offering":[153],"scalable":[155],"solution":[156],"for":[157],"category-agnostic":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-08T00:00:00"}