{"id":"https://openalex.org/W4404355685","doi":"https://doi.org/10.48550/arxiv.2411.02293","title":"Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation","display_name":"Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation","publication_year":2024,"publication_date":"2024-11-04","ids":{"openalex":"https://openalex.org/W4404355685","doi":"https://doi.org/10.48550/arxiv.2411.02293"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.02293","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.02293","pdf_url":"https://arxiv.org/pdf/2411.02293","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.02293","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103089178","display_name":"Xianghui Yang","orcid":"https://orcid.org/0000-0003-3308-3108","observed_orcids":["https://orcid.org/0000-0003-3308-3108"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xianghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026199715","display_name":"Huiwen Shi","orcid":"https://orcid.org/0000-0003-2713-9507","observed_orcids":["https://orcid.org/0000-0003-2713-9507"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Huiwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Bowen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087949383","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-5972-5466","observed_orcids":["https://orcid.org/0000-0002-5972-5466"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018181104","display_name":"Jiacheng Wang","orcid":"https://orcid.org/0000-0003-2595-265X","observed_orcids":["https://orcid.org/0000-0003-2595-265X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiacheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071831230","display_name":"Hongxu Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Hongxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007736125","display_name":"Xinhai Liu","orcid":"https://orcid.org/0000-0003-4200-4862","observed_orcids":["https://orcid.org/0000-0003-4200-4862"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xinhai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063636252","display_name":"Xinzhou Wang","orcid":"https://orcid.org/0000-0003-3972-3073","observed_orcids":["https://orcid.org/0000-0003-3972-3073","https://orcid.org/0009-0003-4678-3557","https://orcid.org/0009-0009-0943-0027"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xinzhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066989412","display_name":"Qingxiang Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Qingxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050610245","display_name":"Jiaao Yu","orcid":"https://orcid.org/0009-0008-2243-5933","observed_orcids":["https://orcid.org/0009-0008-2243-5933"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Jiaao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Lifu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lifu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xu, Jing","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"He, Zebin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Zebin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345101","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0003-1597-9058","observed_orcids":["https://orcid.org/0000-0003-1597-9058"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100684828","display_name":"Sicong Liu","orcid":"https://orcid.org/0000-0003-4402-1260","observed_orcids":["https://orcid.org/0000-0003-4402-1260","https://orcid.org/0000-0003-1612-4844"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Sicong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wu, Junta","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Junta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lian, Yihang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lian, Yihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yang, Shaoxiong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Shaoxiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005799407","display_name":"Yuhong Liu","orcid":"https://orcid.org/0000-0002-2565-8701","observed_orcids":["https://orcid.org/0000-0002-2565-8701"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111595030","display_name":"Yong Yang","orcid":"https://orcid.org/0000-0001-9467-0942","observed_orcids":["https://orcid.org/0000-0001-9467-0942","https://orcid.org/0009-0005-0778-9301","https://orcid.org/0000-0003-2983-8395"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Di","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Di","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiang, Jie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034317074","display_name":"Chunchao Guo","orcid":"https://orcid.org/0009-0001-7465-802X","observed_orcids":["https://orcid.org/0009-0001-7465-802X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Chunchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":112,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.8812999725341797,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.8812999725341797,"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":0.11559999734163284,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.002199999988079071,"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/3d-generation","display_name":"3D generation","score":0.8130000233650208},{"id":"https://openalex.org/keywords/text-to-3d-generation","display_name":"text-to-3D generation","score":0.8730000257492065},{"id":"https://openalex.org/keywords/image-to-3d-generation","display_name":"image-to-3D generation","score":0.9980000257492065},{"id":"https://openalex.org/keywords/multi-view-diffusion-models","display_name":"multi-view diffusion models","score":0.7870000004768372},{"id":"https://openalex.org/keywords/multi-view-image-synthesis","display_name":"multi-view image synthesis","score":0.7149999737739563},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.8040000200271606}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5429449081420898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48970988392829895},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3310452103614807}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.02293","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.02293","pdf_url":"https://arxiv.org/pdf/2411.02293","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.02293","doi":"https://doi.org/10.48550/arxiv.2411.02293","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.02293","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.02293","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.02293","pdf_url":"https://arxiv.org/pdf/2411.02293","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404355685.pdf","grobid_xml":"https://content.openalex.org/works/W4404355685.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W4298187450","https://openalex.org/W4386395766","https://openalex.org/W4387635239","https://openalex.org/W4388555505","https://openalex.org/W4388651092","https://openalex.org/W4389469745","https://openalex.org/W4392489534","https://openalex.org/W4394972252","https://openalex.org/W4402733585","https://openalex.org/W4402951629","https://openalex.org/W4403770461","https://openalex.org/W4404002617","https://openalex.org/W4415797429","https://openalex.org/W6999986475","https://openalex.org/W7134583938"],"related_works":["https://openalex.org/W4397049050","https://openalex.org/W4389116111","https://openalex.org/W4391832484","https://openalex.org/W4388651092","https://openalex.org/W4391014185","https://openalex.org/W4409356503","https://openalex.org/W4391421097","https://openalex.org/W4402753533","https://openalex.org/W4402727662","https://openalex.org/W4406746339"],"abstract_inverted_index":{"While":[0],"3D":[1,14,77,106,144,165],"generative":[2],"models":[3,12],"have":[4],"greatly":[5],"improved":[6],"artists'":[7],"workflows,":[8],"the":[9,51,76,83,91,105,109,128,133,137,143,149,198,203],"existing":[10,179],"diffusion":[11,58,130],"for":[13],"generation":[15,19,194],"suffer":[16],"from":[17,79,85,136],"slow":[18],"and":[20,39,47,102,124,131,163,177,190,200],"poor":[21],"generalization.":[22],"To":[23],"address":[24],"this":[25],"issue,":[26],"we":[27,54,94],"propose":[28],"a":[29,36,40,56,96,156],"two-stage":[30],"approach":[31],"named":[32],"Hunyuan3D":[33,182],"1.0":[34,183],"including":[35],"lite":[37,176],"version":[38,169],"standard":[41,168],"version,":[42],"that":[43,60,100],"both":[44,161],"support":[45,160],"text-":[46,162],"image-conditioned":[48,164],"generation.":[49,166],"In":[50,90],"first":[52],"stage,":[53,93],"employ":[55],"multi-view":[57,63,70,88,111,129],"model":[59,99],"efficiently":[61,141],"generates":[62],"RGB":[64],"in":[65,113],"approximately":[66,114],"4":[67],"seconds.":[68,116],"These":[69],"images":[71,112],"capture":[72],"rich":[73],"details":[74],"of":[75,202],"asset":[78,107],"different":[80],"viewpoints,":[81],"relaxing":[82],"tasks":[84],"single-view":[86],"to":[87,121,140,159],"reconstruction.":[89],"second":[92],"introduce":[95],"feed-forward":[97],"reconstruction":[98,118],"rapidly":[101],"faithfully":[103],"reconstructs":[104],"given":[108],"generated":[110],"7":[115],"The":[117],"network":[119],"learns":[120],"handle":[122],"noises":[123],"in-consistency":[125],"introduced":[126],"by":[127],"leverages":[132],"available":[134],"information":[135],"condition":[138],"image":[139],"recover":[142],"structure.":[145],"Our":[146,167,181],"framework":[147,158],"involves":[148],"text-to-image":[150],"model,":[151],"i.e.,":[152],"Hunyuan-DiT,":[153],"making":[154],"it":[155],"unified":[157],"has":[170],"3x":[171],"more":[172],"parameters":[173],"than":[174],"our":[175],"other":[178],"model.":[180],"achieves":[184],"an":[185],"impressive":[186],"balance":[187],"between":[188],"speed":[189],"quality,":[191],"significantly":[192],"reducing":[193],"time":[195],"while":[196],"maintaining":[197],"quality":[199],"diversity":[201],"produced":[204],"assets.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":63},{"year":2025,"cited_by_count":45},{"year":2024,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-11-15T00:00:00"}
