{"id":"https://openalex.org/W4386794530","doi":"https://doi.org/10.48550/arxiv.2309.07920","title":"Large-Vocabulary 3D Diffusion Model with Transformer","display_name":"Large-Vocabulary 3D Diffusion Model with Transformer","publication_year":2023,"publication_date":"2023-09-14","ids":{"openalex":"https://openalex.org/W4386794530","doi":"https://doi.org/10.48550/arxiv.2309.07920"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.07920","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.07920","pdf_url":"https://arxiv.org/pdf/2309.07920","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.07920","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102234450","display_name":"Ziang Cao","orcid":"https://orcid.org/0009-0003-9239-1001","observed_orcids":["https://orcid.org/0009-0003-9239-1001"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cao, Ziang","raw_affiliation_strings":["S-Lab , Nanyang Technological University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab , Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031455013","display_name":"Fangzhou Hong","orcid":"https://orcid.org/0000-0003-2412-1141","observed_orcids":["https://orcid.org/0000-0003-2412-1141","https://orcid.org/0009-0003-6486-6444"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hong, Fangzhou","raw_affiliation_strings":["S-Lab , Nanyang Technological University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab , Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084010299","display_name":"Tong Wu","orcid":"https://orcid.org/0000-0003-4459-9791","observed_orcids":["https://orcid.org/0000-0003-4459-9791"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wu, Tong","raw_affiliation_strings":["Shanghai AI Laboratory","The Chinese University of Hong Kong ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The Chinese University of Hong Kong ,","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100612025","display_name":"Liang Pan","orcid":"https://orcid.org/0000-0003-1821-4296","observed_orcids":["https://orcid.org/0000-0003-1821-4296"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Pan, Liang","raw_affiliation_strings":["S-Lab , Nanyang Technological University ,","Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab , Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406050","display_name":"Ziwei Liu","orcid":"https://orcid.org/0000-0002-4220-5958","observed_orcids":["https://orcid.org/0000-0002-4220-5958"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Liu, Ziwei","raw_affiliation_strings":["S-Lab , Nanyang Technological University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab , Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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":0.9883000254631042,"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":0.9883000254631042,"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":0.01119999960064888,"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":0.00019999999494757503,"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-object-generation","display_name":"3D object generation","score":0.8690000176429749},{"id":"https://openalex.org/keywords/texture-changes","display_name":"texture changes","score":0.3720000088214874},{"id":"https://openalex.org/keywords/geometry-variation","display_name":"geometry variation","score":0.43799999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7517830729484558},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6164132356643677},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5942417979240417},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.5811835527420044},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5742014646530151},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.517242968082428},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4890492856502533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4303591549396515},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0953158438205719},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.07920","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.07920","pdf_url":"https://arxiv.org/pdf/2309.07920","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.07920","doi":"https://doi.org/10.48550/arxiv.2309.07920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.07920","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.07920","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.07920","pdf_url":"https://arxiv.org/pdf/2309.07920","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2342870495","display_name":null,"funder_award_id":"AcRF\u2010Tier2","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"},{"id":"https://openalex.org/G3527751893","display_name":null,"funder_award_id":"MOET2EP20221-0012","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"},{"id":"https://openalex.org/G6854926366","display_name":null,"funder_award_id":"Tier 2","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"},{"id":"https://openalex.org/G7457883206","display_name":null,"funder_award_id":"RIE2020","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386794530.pdf","grobid_xml":"https://content.openalex.org/works/W4386794530.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2142795561","https://openalex.org/W2601444686","https://openalex.org/W4390718435","https://openalex.org/W4307058054"],"abstract_inverted_index":{"Creating":[0],"diverse":[1,167,229],"and":[2,82,117,125,130,140,157,187,225,251],"high-quality":[3],"3D":[4,18,50,66,75,148,155,159,164,191,195,209,242],"assets":[5],"with":[6,52,105,175,193,218,246],"an":[7],"automatic":[8],"generative":[9,55],"model":[10,104,238],"is":[11],"highly":[12],"desirable.":[13],"Despite":[14],"extensive":[15],"efforts":[16],"on":[17,24,223],"generation,":[19],"most":[20],"existing":[21],"works":[22],"focus":[23],"the":[25,69,89,127,135,144,181,189,202,207,212],"generation":[26,244],"of":[27,48,91,146,153],"a":[28,32,40,53,99,121,151,171,235],"single":[29,54,236],"category":[30],"or":[31],"few":[33],"categories.":[34],"In":[35,198],"this":[36,64,95],"paper,":[37],"we":[38,97,119,142,169,200],"introduce":[39],"diffusion-based":[41],"feed-forward":[42],"framework":[43],"for":[44,63,71,108,215],"synthesizing":[45],"massive":[46],"categories":[47,217],"real-world":[49,92,230],"objects":[51,149],"model.":[56],"Notably,":[57],"there":[58],"are":[59],"three":[60,112],"major":[61],"challenges":[62,110],"large-vocabulary":[65,241],"generation:":[67],"a)":[68],"need":[70],"expressive":[72],"yet":[73],"efficient":[74],"representation;":[76],"b)":[77],"large":[78,247],"diversity":[79],"in":[80,88,138,211],"geometry":[81,139],"texture":[83],"across":[84,184],"categories;":[85],"c)":[86],"complexity":[87],"appearances":[90],"objects.":[93],"To":[94,133,161],"end,":[96],"propose":[98,170],"novel":[100,172],"triplane-based":[101],"3D-aware":[102,173,203],"Diffusion":[103],"TransFormer,":[106],"DiffTF,":[107],"handling":[109,216],"via":[111],"aspects.":[113],"1)":[114],"Considering":[115],"efficiency":[116],"robustness,":[118],"adopt":[120],"revised":[122],"triplane":[123],"representation":[124],"improve":[126],"fitting":[128],"speed":[129],"accuracy.":[131],"2)":[132],"handle":[134],"drastic":[136],"variations":[137],"texture,":[141],"regard":[143],"features":[145],"all":[147],"as":[150],"combination":[152],"generalized":[154,163,190,208],"knowledge":[156,165,192,210],"specialized":[158,194],"features.":[160,196],"extract":[162],"from":[166],"categories,":[168],"transformer":[174],"shared":[176],"cross-plane":[177,182],"attention.":[178],"It":[179],"learns":[180],"relations":[183],"different":[185],"planes":[186],"aggregates":[188],"3)":[197],"addition,":[199],"devise":[201],"encoder/decoder":[204],"to":[205],"enhance":[206],"encoded":[213],"triplanes":[214],"complex":[219],"appearances.":[220],"Extensive":[221],"experiments":[222],"ShapeNet":[224],"OmniObject3D":[226],"(over":[227],"200":[228],"categories)":[231],"convincingly":[232],"demonstrate":[233],"that":[234],"DiffTF":[237],"achieves":[239],"state-of-the-art":[240],"object":[243],"performance":[245],"diversity,":[248],"rich":[249],"semantics,":[250],"high":[252],"quality.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-10T00:00:00"}