{"id":"https://openalex.org/W7225646265","doi":"https://doi.org/10.1145/3842524","title":"Direct3D-V3: Latent-Free Diffusion Transformers in the Native Voxel Domain","display_name":"Direct3D-V3: Latent-Free Diffusion Transformers in the Native Voxel Domain","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225646265","doi":"https://doi.org/10.1145/3842524"},"language":"en","primary_location":{"id":"doi:10.1145/3842524","doi":"https://doi.org/10.1145/3842524","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3842524","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-a","cwts-core","dongbi-a","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3842524","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128017887","display_name":"Shuang Wu","orcid":"https://orcid.org/0009-0002-2939-4448","observed_orcids":["https://orcid.org/0009-0002-2939-4448"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Wu","raw_affiliation_strings":["DreamTech, Shenzhen, China","Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-2939-4448","affiliations":[{"raw_affiliation_string":"DreamTech, Shenzhen, China","institution_ids":[]},{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123050661","display_name":"Jiachen Qian","orcid":"https://orcid.org/0009-0008-5315-9863","observed_orcids":["https://orcid.org/0009-0008-5315-9863","https://orcid.org/0009-0009-0538-5433"]},"institutions":[{"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":["HK"],"is_corresponding":false,"raw_author_name":"Jiachen Qian","raw_affiliation_strings":["DreamTech, Shenzhen, China","The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0009-0538-5433","affiliations":[{"raw_affiliation_string":"DreamTech, Shenzhen, China","institution_ids":[]},{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082510405","display_name":"Youtian Lin","orcid":"https://orcid.org/0000-0002-9179-9406","observed_orcids":["https://orcid.org/0000-0002-9179-9406"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youtian Lin","raw_affiliation_strings":["Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9179-9406","affiliations":[{"raw_affiliation_string":"Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101421861","display_name":"Feihu Zhang","orcid":"https://orcid.org/0000-0003-0712-5722","observed_orcids":["https://orcid.org/0000-0003-0712-5722"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feihu Zhang","raw_affiliation_strings":["DreamTech, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0712-5722","affiliations":[{"raw_affiliation_string":"DreamTech, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042899882","display_name":"Philip H. S. Torr","orcid":"https://orcid.org/0009-0006-0259-5732","observed_orcids":["https://orcid.org/0009-0006-0259-5732"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip Torr","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0006-0259-5732","affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027930243","display_name":"Yao Yao","orcid":"https://orcid.org/0000-0001-9866-4291","observed_orcids":["https://orcid.org/0000-0001-9866-4291"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Yao","raw_affiliation_strings":["Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9866-4291","affiliations":[{"raw_affiliation_string":"Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058572381","display_name":"Xun Cao","orcid":"https://orcid.org/0000-0003-3094-4371","observed_orcids":["https://orcid.org/0000-0003-3094-4371"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Cao","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3094-4371","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"6","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9945999979972839,"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":0.9945999979972839,"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":0.003700000001117587,"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":0.0012000000569969416,"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/diffusion-transformer","display_name":"diffusion transformer","score":0.7599999904632568},{"id":"https://openalex.org/keywords/3d-shape-generation","display_name":"3D shape generation","score":0.7419999837875366},{"id":"https://openalex.org/keywords/signed-distance-function","display_name":"signed distance function","score":0.6610000133514404},{"id":"https://openalex.org/keywords/generative-reconstruction","display_name":"generative reconstruction","score":0.7350000143051147}],"concepts":[{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.9128999710083008},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.7699999809265137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7174999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6262000203132629},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5310999751091003},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C45107383","wikidata":"https://www.wikidata.org/wiki/Q1311829","display_name":"Isosurface","level":3,"score":0.3718999922275543},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3637999892234802},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C165700671","wikidata":"https://www.wikidata.org/wiki/Q203484","display_name":"Laplace operator","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3253999948501587},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C181145010","wikidata":"https://www.wikidata.org/wiki/Q4418033","display_name":"Mesh generation","level":3,"score":0.31049999594688416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3842524","doi":"https://doi.org/10.1145/3842524","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3842524","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-a","cwts-core","dongbi-a","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3842524","doi":"https://doi.org/10.1145/3842524","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3842524","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-a","cwts-core","dongbi-a","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2738551266","https://openalex.org/W4200150166","https://openalex.org/W4300980573","https://openalex.org/W4303647933","https://openalex.org/W4366208220","https://openalex.org/W4385275410","https://openalex.org/W4385275714","https://openalex.org/W4394737230","https://openalex.org/W4400822286","https://openalex.org/W4406746339","https://openalex.org/W4415333916","https://openalex.org/W4416039560","https://openalex.org/W4416958102","https://openalex.org/W4417025030","https://openalex.org/W4417239965","https://openalex.org/W7094944332","https://openalex.org/W7101756695","https://openalex.org/W7106013284","https://openalex.org/W7106694720","https://openalex.org/W7106712580","https://openalex.org/W7106789420","https://openalex.org/W7117299086","https://openalex.org/W7133205559"],"related_works":["https://openalex.org/W4415795573","https://openalex.org/W4412939881","https://openalex.org/W4403888124","https://openalex.org/W7160821693","https://openalex.org/W7133237268","https://openalex.org/W7221758205","https://openalex.org/W4402753533","https://openalex.org/W4406259689","https://openalex.org/W7214550819","https://openalex.org/W4416551066"],"abstract_inverted_index":{"Native":[0],"3D":[1,220],"generation":[2],"has":[3],"largely":[4],"been":[5],"built":[6],"around":[7],"latent":[8,22,49],"diffusion,":[9],"with":[10,242,266,272],"recent":[11],"advances":[12],"concentrating":[13],"on":[14],"stronger":[15],"variational":[16],"autoencoders":[17],"(VAE)":[18],"and":[19,26,51,108,122,138,161,192,239,250],"increasingly":[20],"elaborate":[21],"representations,":[23],"from":[24,181,216],"vecset":[25],"triplanes":[27],"to":[28,157,212,219,259,269,291],"structured":[29],"sparse":[30],"voxels.":[31],"Despite":[32],"their":[33],"architectural":[34],"differences,":[35],"these":[36],"methods":[37],"all":[38],"share":[39],"the":[40,56,72,77,80,88,95,119,125,178,189,198,202,210,214,226,235,273,277],"same":[41],"premise:":[42],"geometry":[43],"is":[44,90,98,264],"first":[45],"compressed":[46],"into":[47,166],"a":[48,105,111],"space":[50],"only":[52],"then":[53],"modeled":[54],"by":[55],"generator.":[57],"This":[58,222],"paradigm":[59],"carries":[60],"two":[61],"intrinsic":[62],"limitations.":[63],"First,":[64],"VAE":[65,89,120],"reconstruction":[66,93,227],"removes":[67,225],"fine":[68],"geometric":[69],"detail":[70],"before":[71],"diffusion":[73,96,113,263],"model":[74,97,179],"ever":[75],"sees":[76],"data.":[78],"Second,":[79],"two-stage":[81],"pipeline":[82],"creates":[83],"an":[84,150,206,232],"objective":[85,233],"mismatch,":[86],"since":[87],"trained":[91,99],"for":[92,100],"whereas":[94],"distribution":[101],"matching.":[102],"We":[103],"take":[104],"different":[106],"route":[107],"propose":[109],"Direct3D-V3,":[110],"latent-free":[112,223],"transformer":[114],"(DiT)":[115],"framework":[116],"that":[117,172,286],"discards":[118],"altogether":[121],"operates":[123],"in":[124,234],"native":[126,236,251],"voxel":[127,133,144,237,253],"domain,":[128,238],"directly":[129,180],"modeling":[130],"raw":[131],"SDF":[132,164,252],"grids":[134,165],"during":[135],"both":[136],"training":[137,230],"sampling.":[139],"To":[140,185],"make":[141,256],"this":[142],"direct":[143],"formulation":[145],"geometrically":[146],"reliable,":[147],"we":[148],"introduce":[149],"implicit":[151],"manifold":[152],"regularization":[153],"over":[154],"neighboring":[155],"voxels":[156],"suppress":[158],"non-watertight":[159],"surfaces,":[160],"convert":[162],"predicted":[163,183,248],"meshes":[167,241],"via":[168],"Marching":[169],"Cubes":[170],"so":[171],"rendered":[173],"normal":[174],"losses":[175],"can":[176],"supervise":[177],"its":[182],"SDF.":[184],"improve":[186,270],"alignment":[187,271],"between":[188],"conditioning":[190,203],"image":[191,204,217],"generated":[193],"geometry,":[194],"Direct3D-V3":[195,257,287],"also":[196],"predicts":[197],"camera":[199,249],"parameters":[200],"of":[201],"as":[205],"auxiliary":[207],"task,":[208],"encouraging":[209],"DiT":[211],"learn":[213],"mapping":[215],"observations":[218],"shape.":[221],"design":[224],"bottleneck,":[228],"brings":[229],"under":[231],"yields":[240],"substantially":[243],"richer":[244],"local":[245],"detail.":[246],"The":[247],"output":[254],"further":[255],"extensible":[258],"generative":[260,278],"reconstruction,":[261],"where":[262],"interleaved":[265],"normal-guided":[267],"refinement":[268],"observed":[274],"view":[275],"while":[276,295],"prior":[279],"completes":[280],"unseen":[281],"regions.":[282],"Extensive":[283],"experiments":[284],"show":[285],"achieves":[288],"competitive":[289],"results":[290],"state-of-the-art":[292],"latent-based":[293],"methods,":[294],"producing":[296],"finer":[297],"geometry.":[298]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}