{"id":"https://openalex.org/W4409206018","doi":"https://doi.org/10.1007/s11263-025-02423-5","title":"AvatarStudio: High-Fidelity and Animatable 3D Avatar Creation from Text","display_name":"AvatarStudio: High-Fidelity and Animatable 3D Avatar Creation from Text","publication_year":2025,"publication_date":"2025-04-07","ids":{"openalex":"https://openalex.org/W4409206018","doi":"https://doi.org/10.1007/s11263-025-02423-5"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02423-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02423-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02423-5.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02423-5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082653986","display_name":"Xuanmeng Zhang","orcid":"https://orcid.org/0000-0002-6939-4074"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Xuanmeng Zhang","raw_affiliation_strings":["ReLER Lab, AAII, University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6939-4074","affiliations":[{"raw_affiliation_string":"ReLER Lab, AAII, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029002447","display_name":"Jianfeng Zhang","orcid":"https://orcid.org/0000-0003-1686-9010"},"institutions":[{"id":"https://openalex.org/I1325159990","display_name":"Ministry of Defence","ror":"https://ror.org/05m38qe70","country_code":"SG","type":"government","lineage":["https://openalex.org/I1325159990"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jianfeng Zhang","raw_affiliation_strings":["ByteDance Seed, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed, Singapore, Singapore","institution_ids":["https://openalex.org/I1325159990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046566373","display_name":"Chenxu Zhang","orcid":"https://orcid.org/0000-0003-1645-9695"},"institutions":[{"id":"https://openalex.org/I1325159990","display_name":"Ministry of Defence","ror":"https://ror.org/05m38qe70","country_code":"SG","type":"government","lineage":["https://openalex.org/I1325159990"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chenxu Zhang","raw_affiliation_strings":["ByteDance Seed, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed, Singapore, Singapore","institution_ids":["https://openalex.org/I1325159990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014937540","display_name":"Jun Hao Liew","orcid":"https://orcid.org/0000-0002-7538-6759"},"institutions":[{"id":"https://openalex.org/I1325159990","display_name":"Ministry of Defence","ror":"https://ror.org/05m38qe70","country_code":"SG","type":"government","lineage":["https://openalex.org/I1325159990"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jun Hao Liew","raw_affiliation_strings":["ByteDance Seed, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed, Singapore, Singapore","institution_ids":["https://openalex.org/I1325159990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063191044","display_name":"Huichao Zhang","orcid":"https://orcid.org/0000-0002-2779-5419"},"institutions":[{"id":"https://openalex.org/I1325159990","display_name":"Ministry of Defence","ror":"https://ror.org/05m38qe70","country_code":"SG","type":"government","lineage":["https://openalex.org/I1325159990"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huichao Zhang","raw_affiliation_strings":["ByteDance Seed, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed, Singapore, Singapore","institution_ids":["https://openalex.org/I1325159990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084370585","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-6794-2241"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["ReLER Lab, CCAI, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ReLER Lab, CCAI, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087024287","display_name":"Jiashi Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I1325159990","display_name":"Ministry of Defence","ror":"https://ror.org/05m38qe70","country_code":"SG","type":"government","lineage":["https://openalex.org/I1325159990"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiashi Feng","raw_affiliation_strings":["ByteDance Seed, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed, Singapore, Singapore","institution_ids":["https://openalex.org/I1325159990"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5082653986"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":1.0663,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71355301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"133","issue":"8","first_page":"5178","last_page":"5196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9990000128746033,"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/T12290","display_name":"Human Motion and Animation","score":0.9990000128746033,"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":0.9983999729156494,"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/avatar","display_name":"Avatar","score":0.8685832023620605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6365962624549866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.554837703704834},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4895111322402954},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4862319529056549},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4340585470199585},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43140077590942383},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.39867550134658813},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.25582653284072876}],"concepts":[{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.8685832023620605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6365962624549866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.554837703704834},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4895111322402954},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4862319529056549},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4340585470199585},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43140077590942383},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.39867550134658813},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25582653284072876},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-025-02423-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02423-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02423-5.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-025-02423-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02423-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02423-5.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320967","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409206018.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2052069724","https://openalex.org/W2178629455","https://openalex.org/W2963876278","https://openalex.org/W2978956737","https://openalex.org/W3106672182","https://openalex.org/W3109585842","https://openalex.org/W3135367836","https://openalex.org/W3167491448","https://openalex.org/W3201927751","https://openalex.org/W3202366118","https://openalex.org/W3202804820","https://openalex.org/W3212516020","https://openalex.org/W3213433499","https://openalex.org/W4210984894","https://openalex.org/W4214770715","https://openalex.org/W4221151978","https://openalex.org/W4283025171","https://openalex.org/W4286611314","https://openalex.org/W4294959213","https://openalex.org/W4306820534","https://openalex.org/W4312708649","https://openalex.org/W4312933868","https://openalex.org/W4321231831","https://openalex.org/W4377864432","https://openalex.org/W4385318467","https://openalex.org/W4385483120","https://openalex.org/W4385537219","https://openalex.org/W4386065887","https://openalex.org/W4386075992","https://openalex.org/W4390872905","https://openalex.org/W4390873054","https://openalex.org/W4390873542","https://openalex.org/W4390874184","https://openalex.org/W4393148031","https://openalex.org/W4394625831","https://openalex.org/W4399563927","https://openalex.org/W4402713106","https://openalex.org/W4402774699","https://openalex.org/W6631190155","https://openalex.org/W6843813467","https://openalex.org/W6844223692","https://openalex.org/W6853757692","https://openalex.org/W6856304189","https://openalex.org/W6858911792"],"related_works":["https://openalex.org/W3138471234","https://openalex.org/W4247958311","https://openalex.org/W4396832849","https://openalex.org/W1584662471","https://openalex.org/W2785089443","https://openalex.org/W2265117524","https://openalex.org/W1467576422","https://openalex.org/W4220730560","https://openalex.org/W2969390373","https://openalex.org/W2604471456"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"study":[2],"the":[3,70,89,110,113],"problem":[4],"of":[5,88],"creating":[6],"high-fidelity":[7],"and":[8,38,78,85,117,143],"animatable":[9,33,59],"3D":[10,56],"avatars":[11,24,34,125],"from":[12,126],"only":[13],"textual":[14],"descriptions.":[15],"Existing":[16],"text-to-avatar":[17],"methods":[18],"are":[19],"either":[20],"limited":[21],"to":[22,31,65,74,149],"static":[23],"which":[25],"cannot":[26],"be":[27],"animated":[28],"or":[29],"struggle":[30],"generate":[32],"with":[35],"promising":[36],"quality":[37],"precise":[39],"pose":[40,86],"control.":[41],"To":[42,81],"address":[43],"these":[44],"limitations,":[45],"we":[46,92],"propose":[47],"AvatarStudio,":[48],"a":[49,94],"generative":[50],"model":[51,98],"that":[52],"yields":[53],"explicit":[54,71],"textured":[55],"meshes":[57],"for":[58,102,129,135,153],"human":[60],"avatars.":[61],"Specifically,":[62],"AvatarStudio":[63,121],"proposes":[64],"incorporate":[66],"articulation":[67],"modeling":[68],"into":[69],"mesh":[72,115],"representation":[73,116],"support":[75],"high-resolution":[76],"rendering":[77],"avatar":[79,141,145],"animation.":[80,130],"ensure":[82],"view":[83],"consistency":[84],"controllability":[87],"resulting":[90],"avatars,":[91],"introduce":[93],"simple-yet-effective":[95],"2D":[96],"diffusion":[97,119],"conditioned":[99],"on":[100],"DensePose":[101],"Score":[103],"Distillation":[104],"Sampling":[105],"supervision.":[106],"By":[107],"effectively":[108],"leveraging":[109],"synergy":[111],"between":[112],"articulated":[114],"DensePose-conditional":[118],"model,":[120],"can":[122],"create":[123],"high-quality":[124],"text":[127],"ready":[128],"Furthermore,":[131],"it":[132],"is":[133],"competent":[134],"many":[136],"applications,":[137],"e.g.":[138],",":[139],"multimodal":[140],"animations":[142],"style-guided":[144],"creation.":[146],"Please":[147],"refer":[148],"our":[150],"project":[151],"page":[152],"more":[154],"results.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
