{"id":"https://openalex.org/W4417125820","doi":"https://doi.org/10.1145/3757377.3763812","title":"ShapeGen: Towards High-Quality 3D Shape Synthesis","display_name":"ShapeGen: Towards High-Quality 3D Shape Synthesis","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417125820","doi":"https://doi.org/10.1145/3757377.3763812"},"language":null,"primary_location":{"id":"doi:10.1145/3757377.3763812","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","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/A5069733636","display_name":"Yangguang Li","orcid":"https://orcid.org/0000-0002-6090-3899"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Yangguang Li","raw_affiliation_strings":["CUHK, Hong Kong, China and VAST, Beijing, China"],"affiliations":[{"raw_affiliation_string":"CUHK, Hong Kong, China and VAST, Beijing, China","institution_ids":["https://openalex.org/I75689368","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022458011","display_name":"Xianglong He","orcid":"https://orcid.org/0000-0001-5368-0765"},"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":"Xianglong He","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023236842","display_name":"Zi\u2013Xin Zou","orcid":"https://orcid.org/0000-0003-2945-552X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zi-Xin Zou","raw_affiliation_strings":["VAST, Beijing, China"],"affiliations":[{"raw_affiliation_string":"VAST, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003441336","display_name":"Z Liu","orcid":"https://orcid.org/0009-0007-8287-8499"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zexiang Liu","raw_affiliation_strings":["VAST, Beijing, China"],"affiliations":[{"raw_affiliation_string":"VAST, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wanli Ouyang","raw_affiliation_strings":["CUHK, HongKong, China and Shanghai Artificial Intelligence Laboratory, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"CUHK, HongKong, China and Shanghai Artificial Intelligence Laboratory, Hong Kong, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751872","display_name":"Ding Liang","orcid":"https://orcid.org/0000-0001-9774-4687"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding Liang","raw_affiliation_strings":["VAST, Beijing, China"],"affiliations":[{"raw_affiliation_string":"VAST, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091525681","display_name":"Yan\u2010Pei Cao","orcid":"https://orcid.org/0000-0002-0416-4374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan-Pei Cao","raw_affiliation_strings":["VAST, Beijing, China"],"affiliations":[{"raw_affiliation_string":"VAST, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5069733636"],"corresponding_institution_ids":["https://openalex.org/I75689368","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40072788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.5960000157356262,"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":0.5960000157356262,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3264000117778778,"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":0.02889999933540821,"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/softmax-function","display_name":"Softmax function","score":0.5253000259399414},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49140000343322754},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43860000371932983},{"id":"https://openalex.org/keywords/aliasing","display_name":"Aliasing","score":0.42080000042915344},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.3962000012397766},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3882000148296356},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.37310001254081726},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.35260000824928284},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.31610000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7469000220298767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6154999732971191},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.5253000259399414},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49140000343322754},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.42080000042915344},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40549999475479126},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3027999997138977},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757377.3763812","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","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":23,"referenced_works":["https://openalex.org/W2178629455","https://openalex.org/W2342277278","https://openalex.org/W2963627347","https://openalex.org/W3177150154","https://openalex.org/W3180196270","https://openalex.org/W3201927751","https://openalex.org/W4229035826","https://openalex.org/W4311034203","https://openalex.org/W4312933868","https://openalex.org/W4313036632","https://openalex.org/W4385275714","https://openalex.org/W4385318467","https://openalex.org/W4386047807","https://openalex.org/W4386075660","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4400822286","https://openalex.org/W4402733585","https://openalex.org/W4402753669","https://openalex.org/W4402753761","https://openalex.org/W4413145781","https://openalex.org/W4413146851","https://openalex.org/W4415795573"],"related_works":[],"abstract_inverted_index":{"Inspired":[0],"by":[1,62,141,190],"generative":[2],"paradigms":[3],"in":[4,112,268],"image":[5,159],"and":[6,42,79,85,123,131,137,162,181,196,216],"video,":[7],"3D":[8,21,51,77,102,157],"shape":[9,74],"generation":[10,75,129,170,236],"has":[11],"made":[12],"notable":[13],"progress,":[14],"enabling":[15],"the":[16,34,49,59,86,94,128,154,163,197,206,246,257],"rapid":[17],"synthesis":[18],"of":[19,36,57,88,156,165,224,248,260],"high-fidelity":[20],"assets":[22,52,96],"from":[23,200],"a":[24,221,265,272],"single":[25],"image.":[26],"However,":[27],"current":[28],"methods":[29],"still":[30,53],"face":[31],"challenges,":[32],"including":[33],"lack":[35],"intricate":[37],"details,":[38],"overly":[39],"smoothed":[40],"surfaces,":[41],"fragmented":[43,138],"thin-shell":[44,139],"structures.":[45],"These":[46,91],"limitations":[47],"leave":[48],"generated":[50,95],"one":[54],"step":[55],"short":[56],"meeting":[58],"standards":[60],"favored":[61],"artists.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,244],"present":[68],"ShapeGen,":[69],"which":[70],"achieves":[71,264],"high-quality":[72],"image-to-3D":[73,269],"through":[76],"representation":[78,145],"supervision":[80,125],"improvements,":[81],"resolution":[82,155],"scaling":[83,232],"up,":[84],"advantages":[87],"linear":[89,211],"transformers.":[90],"advancements":[92],"allow":[93],"to":[97,114,168,213,256],"be":[98],"seamlessly":[99],"integrated":[100],"into":[101],"pipelines,":[103],"facilitating":[104],"their":[105],"widespread":[106],"adoption":[107],"across":[108],"various":[109],"applications.":[110],"Specifically,":[111],"contrast":[113],"existing":[115],"methods:":[116],"1)":[117],"We":[118,151,173,204,228],"investigate":[119],"how":[120],"different":[121],"representations":[122],"VAE":[124],"strategies":[126],"affect":[127],"process,":[130],"address":[132],"issues":[133],"like":[134],"aliasing":[135],"artifacts":[136],"structures":[140],"using":[142,177],"an":[143,230],"TSDF-based":[144],"supervised":[146],"with":[147,210],"BCE":[148],"loss.":[149],"2)":[150],"scale":[152],"up":[153],"data,":[158],"conditioning":[160,176],"inputs,":[161],"number":[164,223],"latent":[166,225],"tokens":[167],"enhance":[169],"fidelity.":[171],"3)":[172],"adopt":[174],"mixed":[175],"raw":[178],"RGB":[179,194],"images":[180,195],"normal":[182],"maps":[183],"during":[184],"training,":[185],"effectively":[186],"resolving":[187],"ambiguities":[188],"caused":[189],"inconsistencies":[191],"between":[192],"ControlNet-generated":[193],"underlying":[198],"geometry":[199],"untextured":[201],"assets.":[202],"4)":[203],"replace":[205],"original":[207],"softmax":[208],"attention":[209,212],"improve":[214],"training":[215],"inference":[217],"efficiency":[218],"when":[219],"handling":[220],"large":[222],"tokens.":[226],"5)":[227],"introduce":[229],"inference-time":[231],"strategy":[233],"that":[234],"enhances":[235],"quality":[237],"at":[238],"test":[239],"time.":[240],"Through":[241],"extensive":[242],"experiments,":[243],"validate":[245],"impact":[247],"these":[249,261],"improvements":[250],"on":[251],"overall":[252],"performance.":[253,275],"Ultimately,":[254],"thanks":[255],"synergistic":[258],"effects":[259],"enhancements,":[262],"ShapeGen":[263],"significant":[266],"leap":[267],"generation,":[270],"establishing":[271],"new":[273],"state-of-the-art":[274]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-08T00:00:00"}