{"id":"https://openalex.org/W4384389892","doi":"https://doi.org/10.1145/3581783.3612022","title":"AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion","display_name":"AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4384389892","doi":"https://doi.org/10.1145/3581783.3612022"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612022","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2307.06526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103324866","display_name":"Shuo Huang","orcid":"https://orcid.org/0009-0004-7100-1067"},"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":true,"raw_author_name":"Shuo Huang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020316185","display_name":"Zongxin Yang","orcid":"https://orcid.org/0000-0001-8783-8313"},"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":"Zongxin Yang","raw_affiliation_strings":["ReLER, CCAI, Zhejiang University, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"ReLER, CCAI, Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092474567","display_name":"Liangting Li","orcid":"https://orcid.org/0009-0005-2265-4026"},"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":"Liangting Li","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"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, CCAI, Zhejiang University, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"ReLER, CCAI, Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039477812","display_name":"Jia Jia","orcid":"https://orcid.org/0009-0005-8449-278X"},"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":"Jia Jia","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University &amp; Beijing National Research Center for Information Science and Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University &amp; Beijing National Research Center for Information Science and Technology, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103324866"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.8189,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.94320221,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5734","last_page":"5745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8187196850776672},{"id":"https://openalex.org/keywords/clothing","display_name":"Clothing","score":0.8092743158340454},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.7814207077026367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5421645641326904},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5330789089202881},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.47577133774757385},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45055556297302246},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4158763885498047},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.36741745471954346},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.29960083961486816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187196850776672},{"id":"https://openalex.org/C530175646","wikidata":"https://www.wikidata.org/wiki/Q11460","display_name":"Clothing","level":2,"score":0.8092743158340454},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.7814207077026367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5421645641326904},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5330789089202881},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.47577133774757385},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45055556297302246},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4158763885498047},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36741745471954346},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29960083961486816},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612022","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2307.06526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.06526","pdf_url":"https://arxiv.org/pdf/2307.06526","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.06526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.06526","pdf_url":"https://arxiv.org/pdf/2307.06526","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2295355433","https://openalex.org/W2903365351","https://openalex.org/W2962974533","https://openalex.org/W2963800363","https://openalex.org/W2979652999","https://openalex.org/W3034968345","https://openalex.org/W3035619198","https://openalex.org/W3035668851","https://openalex.org/W3107036647","https://openalex.org/W3109394508","https://openalex.org/W3141954417","https://openalex.org/W3153220274","https://openalex.org/W3154906787","https://openalex.org/W3174541392","https://openalex.org/W3180196270","https://openalex.org/W3183544223","https://openalex.org/W3202804820","https://openalex.org/W3203514471","https://openalex.org/W3216551675","https://openalex.org/W4200150166","https://openalex.org/W4205474609","https://openalex.org/W4214731463","https://openalex.org/W4235375376","https://openalex.org/W4281485151","https://openalex.org/W4311805945","https://openalex.org/W4312453532","https://openalex.org/W4312708649","https://openalex.org/W4312933868","https://openalex.org/W4312935996","https://openalex.org/W4313041309","https://openalex.org/W4321231831","https://openalex.org/W4390874304","https://openalex.org/W6600741150","https://openalex.org/W6610578020"],"related_works":["https://openalex.org/W3138471234","https://openalex.org/W4247958311","https://openalex.org/W2738456166","https://openalex.org/W2785089443","https://openalex.org/W2265117524","https://openalex.org/W4312431072","https://openalex.org/W2352745894","https://openalex.org/W2057731951","https://openalex.org/W1467576422","https://openalex.org/W4220730560"],"abstract_inverted_index":{"Large-scale":[0],"pre-trained":[1],"vision-language":[2],"models":[3,23,41],"allow":[4],"for":[5,59,88,161],"the":[6,37,50,60,75,97,102,119,142,158,191],"zero-shot":[7,162],"text-based":[8],"generation":[9,143],"of":[10,39,144,152,193],"3D":[11],"avatars.":[12,52,194],"The":[13],"previous":[14,173],"state-of-the-art":[15],"method":[16],"utilized":[17],"CLIP":[18,54],"to":[19,78,84,117],"supervise":[20],"neural":[21,105],"implicit":[22,106],"that":[24,109,169],"reconstructed":[25],"a":[26,80,111,131,150],"human":[27],"body":[28,145],"mesh.":[29],"However,":[30],"this":[31],"approach":[32],"has":[33],"two":[34],"limitations.":[35],"Firstly,":[36],"lack":[38],"avatar-specific":[40],"can":[42,189],"cause":[43],"facial":[44],"distortion":[45],"and":[46,122,146,148],"unrealistic":[47],"clothing":[48,95,123,153],"in":[49,64,125,179],"generated":[51],"Secondly,":[53],"only":[55],"provides":[56],"optimization":[57,133],"direction":[58],"overall":[61],"appearance,":[62],"resulting":[63],"less":[65],"impressive":[66],"results.":[67],"To":[68],"address":[69],"these":[70],"limitations,":[71],"we":[72,156,188],"propose":[73],"AvatarFusion,":[74],"first":[76,103,159],"framework":[77,171],"use":[79],"latent":[81],"diffusion":[82],"model":[83,108,185],"provide":[85],"pixel-level":[86],"guidance":[87],"generating":[89],"human-realistic":[90],"avatars":[91],"while":[92],"simultaneously":[93],"segmenting":[94],"from":[96],"avatar's":[98],"body.":[99],"AvatarFusion":[100],"includes":[101],"clothing-decoupled":[104],"avatar":[107],"employs":[110],"novel":[112,132],"Dual":[113],"Volume":[114],"Rendering":[115],"strategy":[116],"render":[118],"decoupled":[120],"skin":[121],"sub-models":[124],"one":[126],"space.":[127],"We":[128],"also":[129],"introduce":[130],"method,":[134],"called":[135],"Pixel-Semantics":[136],"Difference-Sampling":[137],"(PS-DS),":[138],"which":[139],"semantically":[140],"separates":[141],"clothes,":[147],"generates":[149],"variety":[151],"styles.":[154],"Moreover,":[155],"establish":[157],"benchmark":[160],"text-to-avatar":[163],"generation.":[164],"Our":[165],"experimental":[166],"results":[167],"demonstrate":[168],"our":[170,184,199],"outperforms":[172],"approaches,":[174],"with":[175],"significant":[176],"improvements":[177],"observed":[178],"all":[180],"metrics.":[181],"Additionally,":[182],"since":[183],"is":[186],"clothing-decoupled,":[187],"exchange":[190],"clothes":[192],"Code":[195],"are":[196],"available":[197],"on":[198],"project":[200],"page":[201],"https://hansenhuang0823.github.io/AvatarFusion.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":14}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
