{"id":"https://openalex.org/W7131095348","doi":"https://doi.org/10.1109/iccvw69036.2025.00687","title":"High-Fidelity Character Animation: Generating Coherent and Controllable Motion Videos from Static Images","display_name":"High-Fidelity Character Animation: Generating Coherent and Controllable Motion Videos from Static Images","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131095348","doi":"https://doi.org/10.1109/iccvw69036.2025.00687"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","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/A5126651836","display_name":"Yongming Huang","orcid":null},"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":"Yongming Huang","raw_affiliation_strings":["School of Automation, Southeast University,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126649205","display_name":"Zhuojun Xia","orcid":null},"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":"Zhuojun Xia","raw_affiliation_strings":["School of Automation, Southeast University,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126603172","display_name":"Can Bu","orcid":null},"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":"Can Bu","raw_affiliation_strings":["School of Automation, Southeast University,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62789677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6651","last_page":"6660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9103000164031982,"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":0.9103000164031982,"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":0.013899999670684338,"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/T11448","display_name":"Face recognition and analysis","score":0.013299999758601189,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6718000173568726},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6664999723434448},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5939000248908997},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5906000137329102},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5590999722480774},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5349000096321106},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5260999798774719},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5167999863624573},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5070000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198000192642212},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6718000173568726},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6664999723434448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6407999992370605},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5939000248908997},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5906000137329102},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5422000288963318},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5349000096321106},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.3416000008583069},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","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":24,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1849277567","https://openalex.org/W2064076387","https://openalex.org/W2096733369","https://openalex.org/W2133665775","https://openalex.org/W2154741421","https://openalex.org/W2471768434","https://openalex.org/W2950689937","https://openalex.org/W2962785568","https://openalex.org/W2963073614","https://openalex.org/W2963876278","https://openalex.org/W2966421984","https://openalex.org/W2969985801","https://openalex.org/W2990503944","https://openalex.org/W3175471114","https://openalex.org/W3178284600","https://openalex.org/W4312473638","https://openalex.org/W4312933868","https://openalex.org/W4386071957","https://openalex.org/W4390872556","https://openalex.org/W4390873054","https://openalex.org/W4390874580","https://openalex.org/W4393148505","https://openalex.org/W4402704510"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,131],"video-driven":[4],"character":[5],"animation,":[6],"which":[7],"aims":[8],"to":[9,69,89,107],"generate":[10],"temporally":[11],"continuous":[12],"and":[13,44,95,115,137,149],"appearance-consistent":[14],"role":[15],"animation":[16],"videos":[17],"from":[18],"static":[19],"images":[20],"using":[21],"pose":[22],"signals.":[23],"Although":[24],"diffusion":[25],"models":[26],"have":[27],"become":[28],"the":[29,71,77,109,126,141,144],"mainstream":[30],"solution,":[31],"existing":[32],"methods":[33],"still":[34],"face":[35],"significant":[36],"challenges":[37],"in":[38,76,152],"cross-frame":[39],"detail":[40],"consistency,":[41],"motion":[42],"controllability,":[43],"long-term":[45],"temporal":[46,117],"modeling.":[47],"To":[48],"address":[49],"these":[50],"limitations,":[51],"we":[52,63,83,99],"propose":[53,84],"High-Fidelity":[54],"Character":[55],"Animation\u2014a":[56],"innovative":[57],"diffusion-based":[58],"video":[59,80,121,155],"generation":[60],"framework.":[61],"First,":[62],"design":[64],"an":[65],"Identity":[66],"Preservation":[67],"Module":[68],"enhance":[70,90],"consistency":[72,118],"of":[73,79,111,128,154],"identity":[74],"features":[75],"process":[78],"generation.":[81],"Second,":[82],"Domain":[85],"Specific":[86],"Adaptation":[87],"Optimization":[88,103],"generalization":[91],"across":[92,119],"diverse":[93],"scenarios":[94],"complex":[96],"poses.":[97],"Fianlly,":[98],"develop":[100],"a":[101],"Spatio-temporal":[102],"with":[104],"Detail":[105],"Enhancement":[106],"improve":[108],"representation":[110],"key":[112],"region":[113],"details":[114],"ensure":[116],"long":[120],"sequences.":[122],"Experiments":[123],"show":[124],"that":[125],"performance":[127],"our":[129],"model":[130],"two":[132],"benchmark":[133],"datasets":[134],"(TikTok":[135],"dataset":[136],"TED-talks":[138],"dataset)":[139],"achieves":[140],"state-of-the-art,":[142],"exceeding":[143],"strongest":[145],"baselines":[146],"by":[147],"22.8%":[148],"30.2%":[150],"respectively":[151],"terms":[153],"quality":[156],"metrics.":[157]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-02-24T00:00:00"}