{"id":"https://openalex.org/W4403792297","doi":"https://doi.org/10.1145/3664647.3681634","title":"Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models","display_name":"Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792297","doi":"https://doi.org/10.1145/3664647.3681634"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681634","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5066140334","display_name":"Haibo Yang","orcid":"https://orcid.org/0009-0006-6521-2145"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haibo Yang","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-6521-2145","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083113249","display_name":"Yang Chen","orcid":"https://orcid.org/0009-0001-9058-5051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Chen","raw_affiliation_strings":["HiDream.ai Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-9058-5051","affiliations":[{"raw_affiliation_string":"HiDream.ai Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085403640","display_name":"Yingwei Pan","orcid":"https://orcid.org/0000-0002-4344-8898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingwei Pan","raw_affiliation_strings":["HiDream.ai Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4344-8898","affiliations":[{"raw_affiliation_string":"HiDream.ai Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["HiDream.ai Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7587-101X","affiliations":[{"raw_affiliation_string":"HiDream.ai Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080463909","display_name":"Zhineng Chen","orcid":"https://orcid.org/0000-0003-1543-6889"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhineng Chen","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1543-6889","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010722442","display_name":"Chong\u2010Wah Ngo","orcid":"https://orcid.org/0000-0003-4182-8261"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chong-Wah Ngo","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-4182-8261","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101517779","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0002-5990-7307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["HiDream.ai Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5990-7307","affiliations":[{"raw_affiliation_string":"HiDream.ai Inc., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5066140334"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":6.6091,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.97813996,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6870","last_page":"6879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9998000264167786,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9998000264167786,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9994999766349792,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9983999729156494,"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":0.6587213277816772},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.575375497341156},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.559139609336853},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.510637104511261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5001604557037354},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.46258828043937683},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4552024006843567},{"id":"https://openalex.org/keywords/high-resolution","display_name":"High resolution","score":0.454015851020813},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4469067454338074},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.11587226390838623},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.10058042407035828},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07762837409973145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6587213277816772},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.575375497341156},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.559139609336853},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.510637104511261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5001604557037354},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.46258828043937683},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4552024006843567},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.454015851020813},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4469067454338074},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.11587226390838623},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.10058042407035828},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07762837409973145},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681634","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2944579304","https://openalex.org/W2962785568","https://openalex.org/W2981876524","https://openalex.org/W2982192816","https://openalex.org/W3109585842","https://openalex.org/W3216476011","https://openalex.org/W4285102264","https://openalex.org/W4312933868","https://openalex.org/W4312969460","https://openalex.org/W4385275714","https://openalex.org/W4386076002","https://openalex.org/W4386076018","https://openalex.org/W4387969239","https://openalex.org/W4388189411","https://openalex.org/W4388191573","https://openalex.org/W4390871705","https://openalex.org/W4390871887","https://openalex.org/W4390874424","https://openalex.org/W4390889720","https://openalex.org/W4402702910","https://openalex.org/W4402733584","https://openalex.org/W4402733585","https://openalex.org/W4402753339","https://openalex.org/W4404534712"],"related_works":["https://openalex.org/W2362774332","https://openalex.org/W4249245269","https://openalex.org/W2765548132","https://openalex.org/W2025681766","https://openalex.org/W2542402767","https://openalex.org/W3023086044","https://openalex.org/W2294441925","https://openalex.org/W4212954839","https://openalex.org/W2142226356","https://openalex.org/W2056165575"],"abstract_inverted_index":{"Despite":[0],"having":[1],"tremendous":[2],"progress":[3],"in":[4,19,22,73,86],"image-to-3D":[5],"generation,":[6],"existing":[7],"methods":[8],"still":[9],"struggle":[10],"to":[11,52,80,117,146,169],"produce":[12,170],"multi-view":[13,53,105,122,130,172],"consistent":[14],"images":[15,54,106,123,131,174],"with":[16,98,107,124,135,175],"high-resolution":[17,125,129],"textures":[18],"detail,":[20],"especially":[21],"the":[23,68,93,121],"paradigm":[24,46],"of":[25],"2D":[26],"diffusion":[27,44,75,96],"that":[28,47,77,165],"lacks":[29],"3D":[30,87,139,151],"awareness.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"present":[36],"High-resolution":[37],"Image-to-3D":[38],"model":[39,76,97],"(Hi3D),":[40],"a":[41,49],"new":[42],"video":[43,62,74,95],"based":[45],"redefines":[48],"single":[50,161],"image":[51,58],"as":[55],"3D-aware":[56,99,112],"sequential":[57],"generation":[59],"(i.e.,":[60],"orbital":[61],"generation).":[63],"This":[64],"methodology":[65],"delves":[66],"into":[67],"underlying":[69],"temporal":[70],"consistency":[71,82,173],"knowledge":[72],"generalizes":[78],"well":[79],"geometry":[81],"across":[83],"multiple":[84],"views":[85,137],"generation.":[88],"Technically,":[89],"Hi3D":[90,167],"first":[91],"empowers":[92],"pre-trained":[94],"prior":[100],"(camera":[101],"pose":[102],"condition),":[103],"yielding":[104],"low-resolution":[108],"texture":[109,126],"details.":[110,127],"A":[111],"video-to-video":[113],"refiner":[114],"is":[115],"learnt":[116],"further":[118,133],"scale":[119],"up":[120],"Such":[128],"are":[132,143,182],"augmented":[134],"novel":[136,157],"through":[138],"Gaussian":[140],"Splatting,":[141],"which":[142],"finally":[144],"leveraged":[145],"obtain":[147],"high-fidelity":[148],"meshes":[149],"via":[150],"reconstruction.":[152],"Extensive":[153],"experiments":[154],"on":[155],"both":[156],"view":[158,162],"synthesis":[159],"and":[160,180],"reconstruction":[163],"demonstrate":[164],"our":[166],"manages":[168],"superior":[171],"highly-detailed":[176],"textures.":[177],"Source":[178],"code":[179],"data":[181],"available":[183],"at":[184],"https://github.com/yanghb22-fdu/Hi3D-Official.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}