{"id":"https://openalex.org/W4417098952","doi":"https://doi.org/10.1109/iccv51701.2025.00870","title":"Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians","display_name":"Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417098952","doi":"https://doi.org/10.1109/iccv51701.2025.00870"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.01464","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100595337","display_name":"Quankai Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Quankai Gao","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013165810","display_name":"Iliyan Georgiev","orcid":"https://orcid.org/0000-0002-9655-2138"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iliyan Georgiev","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036138328","display_name":"Tuanfeng Y. Wang","orcid":"https://orcid.org/0000-0002-8180-4988"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuanfeng Y. Wang","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101960524","display_name":"Krishna Kumar Singh","orcid":"https://orcid.org/0000-0002-8066-6835"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Kumar Singh","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082235583","display_name":"Ulrich Neumann","orcid":"https://orcid.org/0000-0001-8977-7112"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ulrich Neumann","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089480358","display_name":"Jae Shin Yoon","orcid":"https://orcid.org/0000-0003-0181-4869"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jae Shin Yoon","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100595337"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36733159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9320","last_page":"9331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.7170000076293945,"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":0.7170000076293945,"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":0.22699999809265137,"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/T11448","display_name":"Face recognition and analysis","score":0.013799999840557575,"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/autoencoder","display_name":"Autoencoder","score":0.6747000217437744},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5789999961853027},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5200999975204468},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.48750001192092896},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4781999886035919},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46700000762939453},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4099000096321106},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.38089999556541443},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.36820000410079956},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3610000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656000256538391},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6747000217437744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6344000101089478},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5789999961853027},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.48750001192092896},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.36820000410079956},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3605000078678131},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.01464","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01464","pdf_url":"https://arxiv.org/pdf/2508.01464","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2508.01464","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.01464","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.01464","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01464","pdf_url":"https://arxiv.org/pdf/2508.01464","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,15,35,47,57,61,92,131,148,161],"generation":[1,17,191,202],"has":[2,18],"made":[3],"significant":[4],"progress,":[5],"however,":[6],"it":[7],"still":[8],"largely":[9],"remains":[10],"at":[11],"the":[12,24,90,120,145],"object-level.":[13],"Feedforward":[14],"scene-level":[16,36,54,93,147],"been":[19],"rarely":[20],"explored":[21],"due":[22],"to":[23,135,159,167,195,199],"lack":[25],"of":[26,29,98,103,119],"models":[27],"capable":[28,97],"scaling-up":[30],"latent":[31,76,109],"representation":[32,77],"learning":[33,78],"on":[34,45,144,169],"data.":[37],"Unlike":[38],"object-level":[39],"generative":[40,80],"models,":[41],"which":[42,111],"are":[43,65],"trained":[44],"well-labeled":[46],"data":[48,133],"in":[49],"a":[50,100,107,127,171],"bounded":[51],"canonical":[52],"space,":[53],"generations":[55],"with":[56],"scenes":[58],"represented":[59],"by":[60],"Gaussian":[62,104],"Splatting":[63],"(3DGS)":[64],"unbounded":[66],"and":[67,116,178,189],"exhibit":[68,179],"scale":[69,137],"inconsistency":[70,138],"across":[71],"different":[72],"scenes,":[73,162],"making":[74],"unified":[75],"for":[79,130],"purposes":[81],"extremely":[82],"challenging.":[83],"In":[84],"this":[85],"paper,":[86],"we":[87,125,152,186],"introduce":[88],"Can3Tok,":[89],"first":[91],"variational":[94],"autoencoder":[95],"(VAE)":[96],"encoding":[99],"large":[101],"number":[102],"primitives":[105],"into":[106],"low-dimensional":[108],"embedding,":[110],"effectively":[112],"captures":[113],"both":[114],"semantic":[115],"spatial":[117],"information":[118],"inputs.":[121],"Beyond":[122],"model":[123],"design,":[124],"propose":[126],"general":[128],"pipeline":[129],"scene":[132,174],"processing":[134],"address":[136],"issue.":[139],"We":[140],"validate":[141],"our":[142,193],"method":[143],"recent":[146],"dataset":[149],"DL3DV-10K,":[150],"where":[151],"found":[153],"that":[154],"only":[155],"Can3Tok":[156],"successfully":[157],"generalizes":[158],"novel":[160],"while":[163],"compared":[164],"methods":[165],"fail":[166],"converge":[168],"even":[170],"few":[172],"hundred":[173],"inputs":[175],"during":[176,183],"training":[177],"zero":[180],"generalization":[181],"ability":[182,198],"inference.":[184],"Finally,":[185],"demonstrate":[187,196],"image-to-3DGS":[188],"text-to-3DGS":[190],"as":[192],"applications":[194],"its":[197],"facilitate":[200],"downstream":[201],"tasks.":[203]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}