{"id":"https://openalex.org/W4406259689","doi":"https://doi.org/10.1109/tpami.2025.3528247","title":"DiffTF++: 3D-Aware Diffusion Transformer for Large-Vocabulary 3D Generation","display_name":"DiffTF++: 3D-Aware Diffusion Transformer for Large-Vocabulary 3D Generation","publication_year":2025,"publication_date":"2025-01-10","ids":{"openalex":"https://openalex.org/W4406259689","doi":"https://doi.org/10.1109/tpami.2025.3528247","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030984"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3528247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3528247","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5040805922","display_name":"Ziang Cao","orcid":"https://orcid.org/0000-0002-5682-9446"},"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":true,"raw_author_name":"Ziang Cao","raw_affiliation_strings":["College of Computing and Data Science, S-Lab, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, S-Lab, Nanyang Technological University, Singapore","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"},"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":"Fangzhou Hong","raw_affiliation_strings":["College of Computing and Data Science, S-Lab, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736875","display_name":"Tong Wu","orcid":"https://orcid.org/0000-0002-8873-0352"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Wu","raw_affiliation_strings":["Graduate Division of Information Engineering, The Chinese University of Hong Kong, China","graduate division of Information Engineering, The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Graduate Division of Information Engineering, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"graduate division of Information Engineering, The Chinese University of Hong Kong, China","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"},"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/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Pan","raw_affiliation_strings":["Shanghai Artificial Intelligent Laboratory, Shanghai, China","Shanghai Artificial Intelligent Laboratory, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligent Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Artificial Intelligent Laboratory, China","institution_ids":["https://openalex.org/I4210100255","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"},"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":"Ziwei Liu","raw_affiliation_strings":["College of Computing and Data Science, S-Lab, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040805922"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":5.6828,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94460955,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"47","issue":"4","first_page":"3018","last_page":"3030"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9699000120162964,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9616000056266785,"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":0.6284298896789551},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5358537435531616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5261659026145935},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4551047086715698},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3898443579673767},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3723674416542053},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3651084303855896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3261534571647644},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1736646592617035},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11501574516296387},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07467484474182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6284298896789551},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5358537435531616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5261659026145935},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4551047086715698},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3898443579673767},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3723674416542053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3651084303855896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3261534571647644},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1736646592617035},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11501574516296387},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07467484474182129},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3528247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3528247","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40030984","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030984","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2020111712","https://openalex.org/W2122572959","https://openalex.org/W2423557781","https://openalex.org/W2964078384","https://openalex.org/W2968257580","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3170841864","https://openalex.org/W3173531806","https://openalex.org/W3176179930","https://openalex.org/W3180196270","https://openalex.org/W3203510176","https://openalex.org/W4214893857","https://openalex.org/W4312453532","https://openalex.org/W4312545288","https://openalex.org/W4312735552","https://openalex.org/W4313021454","https://openalex.org/W4385245566","https://openalex.org/W4386065598","https://openalex.org/W4386065784","https://openalex.org/W4386065887","https://openalex.org/W4386075859","https://openalex.org/W4386113267","https://openalex.org/W4402774212","https://openalex.org/W6687484953","https://openalex.org/W6748208425","https://openalex.org/W6761628794","https://openalex.org/W6765779288","https://openalex.org/W6779823529","https://openalex.org/W6779879114","https://openalex.org/W6780879210","https://openalex.org/W6783713337","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6795892075","https://openalex.org/W6802159354","https://openalex.org/W6802668286","https://openalex.org/W6843226767","https://openalex.org/W6843813467","https://openalex.org/W6846015844","https://openalex.org/W6846275404","https://openalex.org/W6846976392","https://openalex.org/W6847302828","https://openalex.org/W6847371502","https://openalex.org/W6847671982","https://openalex.org/W6850462592","https://openalex.org/W6853592262","https://openalex.org/W6853668808","https://openalex.org/W6856784870","https://openalex.org/W6858397388","https://openalex.org/W6859214663"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W3167549738","https://openalex.org/W2381983017"],"abstract_inverted_index":{"Generating":[0],"diverse":[1],"and":[2,71,75,103,143,157,169,200,210,217,227,239],"high-quality":[3],"3D":[4,14,21,30,97,101,113,130,230],"assets":[5,31],"automatically":[6],"poses":[7],"a":[8,41,45,54,63,126,190],"fundamental":[9],"yet":[10],"challenging":[11],"task":[12],"in":[13,20,73,187,204],"computer":[15],"vision.":[16],"Despite":[17],"extensive":[18],"efforts":[19],"generation,":[22,131],"existing":[23],"optimization-based":[24],"approaches":[25],"struggle":[26],"to":[27,58,85,93,109,137,152,196],"produce":[28],"large-scale":[29],"efficiently.":[32],"Meanwhile,":[33],"feed-forward":[34,56],"methods":[35],"often":[36],"focus":[37],"on":[38,215],"generating":[39],"only":[40],"single":[42,64],"category":[43],"or":[44],"few":[46],"categories,":[47],"limiting":[48],"their":[49],"generalizability.":[50],"Therefore,":[51],"we":[52,80,124,147],"introduce":[53,89],"diffusion-based":[55],"framework":[57],"address":[59],"these":[60],"challenges":[61],"with":[62,99,121,234],"model.":[65],"To":[66],"handle":[67],"the":[68,90,95,106,111,154,162,175,178,181,205,221,228],"large":[69,235],"diversity":[70],"complexity":[72],"geometry":[74],"texture":[76,171],"across":[77],"categories":[78],"efficiently,":[79],"1)":[81],"adopt":[82],"improved":[83],"triplane":[84,144,158],"guarantee":[86],"efficiency;":[87],"2)":[88],"3D-aware":[91,107,118,191],"transformer":[92],"aggregate":[94],"generalized":[96,112],"knowledge":[98],"specialized":[100],"features;":[102],"3)":[104],"devise":[105],"encoder/decoder":[108],"enhance":[110],"knowledge.":[114],"Building":[115],"upon":[116],"our":[117,224],"Diffusion":[119],"model":[120,156],"TransFormer,":[122],"DiffTF,":[123],"propose":[125],"stronger":[127],"version":[128],"for":[129],"i.e.,":[132],"DiffTF++.":[133],"It":[134],"boils":[135],"down":[136],"two":[138,179],"parts:":[139],"multi-view":[140,149],"reconstruction":[141,150,167],"loss":[142,151],"refinement.":[145],"Specifically,":[146],"utilize":[148],"fine-tune":[153],"diffusion":[155],"decoder,":[159],"thereby":[160],"avoiding":[161],"negative":[163],"influence":[164],"caused":[165],"by":[166],"errors":[168],"improving":[170],"synthesis.":[172],"By":[173],"eliminating":[174],"mismatch":[176],"between":[177],"stages,":[180],"generative":[182],"performance":[183,233],"is":[184,194],"enhanced,":[185],"especially":[186],"texture.":[188],"Additionally,":[189],"refinement":[192],"process":[193],"introduced":[195],"filter":[197],"out":[198],"artifacts":[199],"refine":[201],"triplanes,":[202],"resulting":[203],"generation":[206,232],"of":[207,223],"more":[208],"intricate":[209],"reasonable":[211],"details.":[212],"Extensive":[213],"experiments":[214],"ShapeNet":[216],"OmniObject3D":[218],"convincingly":[219],"demonstrate":[220],"effectiveness":[222],"proposed":[225],"modules":[226],"state-of-the-art":[229],"object":[231],"diversity,":[236],"rich":[237],"semantics,":[238],"high":[240],"quality.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}