{"id":"https://openalex.org/W7161716837","doi":"https://doi.org/10.48550/arxiv.2605.16355","title":"Generative 3D Gaussians with Learned Density Control","display_name":"Generative 3D Gaussians with Learned Density Control","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7161716837","doi":"https://doi.org/10.48550/arxiv.2605.16355"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.16355","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16355","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.16355","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101370776","display_name":"Runjie Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Runjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136497255","display_name":"Yan-Pei Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Yan-Pei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136494898","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0003-0856-0865"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136480641","display_name":"Ding Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136481225","display_name":"Yuan-Chen Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yuan-Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7045000195503235,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7045000195503235,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.17599999904632568,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0421999990940094,"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/gaussian","display_name":"Gaussian","score":0.5546000003814697},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.519599974155426},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5174999833106995},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4474000036716461},{"id":"https://openalex.org/keywords/density-estimation","display_name":"Density estimation","score":0.4348999857902527},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4115999937057495},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.4065000116825104},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.396699994802475},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.3901999890804291}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6743000149726868},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5546000003814697},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.519599974155426},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4706999957561493},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4474000036716461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4375999867916107},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.4348999857902527},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.36079999804496765},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3546999990940094},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C181095308","wikidata":"https://www.wikidata.org/wiki/Q1541599","display_name":"Geometric primitive","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C45107383","wikidata":"https://www.wikidata.org/wiki/Q1311829","display_name":"Isosurface","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C89720835","wikidata":"https://www.wikidata.org/wiki/Q1531701","display_name":"Global illumination","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.16355","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16355","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.16355","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16355","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,85,146],"present":[1],"Density-Sampled":[2],"Gaussians":[3,28],"(DeG),":[4],"a":[5,42,54,89,98,124,140,148,166,175,187],"novel":[6],"3D":[7,27,177],"representation":[8,116],"designed":[9],"to":[10,29,102,154,174],"bridge":[11],"the":[12,65,103,131,182,205,212],"gap":[13],"between":[14],"adaptive":[15,59],"rendering":[16,72],"primitives":[17,78,210],"and":[18,68,106,163],"scalable":[19],"generative":[20,136],"modeling.":[21],"Unlike":[22],"existing":[23],"approaches":[24],"that":[25,95,170,195],"constrain":[26],"fixed":[30],"voxel":[31],"grids":[32],"or":[33],"arrays,":[34],"DeG":[35],"models":[36],"Gaussian":[37,69,112],"centers":[38],"as":[39,97],"samples":[40],"from":[41,123],"learnable":[43],"probability":[44],"density":[45,60,67],"function":[46],"defined":[47],"over":[48],"an":[49],"octree.":[50],"This":[51,180],"formulation":[52],"provides":[53],"rigorous":[55],"mathematical":[56],"framework":[57],"for":[58],"control:":[61],"by":[62,128],"jointly":[63],"optimizing":[64],"spatial":[66],"attributes":[70],"under":[71],"supervision,":[73],"our":[74,196],"model":[75,143],"naturally":[76],"concentrates":[77],"in":[79,110,151,201],"regions":[80],"of":[81,208,215],"high":[82],"geometric":[83],"complexity.":[84],"achieve":[86],"this":[87],"via":[88],"new":[90],"render":[91],"loss":[92],"contribution":[93],"gradient":[94],"serves":[96],"fully":[99],"differentiable":[100],"analogue":[101],"discrete":[104],"densification":[105],"pruning":[107],"heuristics":[108],"used":[109],"standard":[111],"Splatting.":[113],"The":[114],"resulting":[115],"is":[117],"highly":[118],"flexible,":[119],"supporting":[120],"variable-resolution":[121],"decoding":[122],"single":[125],"latent":[126,141,172],"code":[127],"simply":[129],"adjusting":[130],"sampling":[132],"budget.":[133],"To":[134],"enable":[135],"synthesis,":[137],"we":[138],"train":[139],"diffusion":[142,153],"on":[144],"DeG.":[145],"identify":[147],"critical":[149],"challenge":[150],"applying":[152],"unordered":[155],"set-structured":[156],"latents,":[157],"which":[158],"can":[159],"significantly":[160],"slow":[161],"convergence,":[162],"propose":[164],"VecSeq,":[165],"canonical":[167],"re-indexing":[168],"mechanism":[169],"anchors":[171],"tokens":[173],"deterministic":[176],"Sobol":[178],"sequence.":[179],"transforms":[181],"ambiguous":[183],"set-generation":[184],"problem":[185],"into":[186],"robust":[188],"sequence":[189],"modeling":[190],"task.":[191],"Extensive":[192],"experiments":[193],"demonstrate":[194],"pipeline":[197],"achieves":[198],"state-of-the-art":[199],"quality":[200],"single-image-to-3D":[202],"generation,":[203],"combining":[204],"structural":[206],"adaptivity":[207],"unstructured":[209],"with":[211],"training":[213],"stability":[214],"grid-based":[216],"methods.":[217]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-20T00:00:00"}