{"id":"https://openalex.org/W7168318112","doi":"https://doi.org/10.48550/arxiv.2607.10237","title":"CoSAG: Compact Semantic Anchor Gaussians via Training-Free Rate-Distortion Coding","display_name":"CoSAG: Compact Semantic Anchor Gaussians via Training-Free Rate-Distortion Coding","publication_year":2026,"publication_date":"2026-07-11","ids":{"openalex":"https://openalex.org/W7168318112","doi":"https://doi.org/10.48550/arxiv.2607.10237"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.10237","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.10237","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,"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":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.2607.10237","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140648501","display_name":"Yuang Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Yuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140648248","display_name":"Jinlong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jinlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140745151","display_name":"Junhong Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Junhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140660877","display_name":"Ruiting Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Ruiting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140601770","display_name":"Wei Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Wei","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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.3531000018119812,"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":0.3531000018119812,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.13740000128746033,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.11129999905824661,"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/embedding","display_name":"Embedding","score":0.5325000286102295},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4659000039100647},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4634999930858612},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4259999990463257},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.40610000491142273},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.3702999949455261},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.34279999136924744},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.3165999948978424},{"id":"https://openalex.org/keywords/terrain","display_name":"Terrain","score":0.31450000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6887000203132629},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5325000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4860999882221222},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36910000443458557},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3312999904155731},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2780575108","wikidata":"https://www.wikidata.org/wiki/Q7316652","display_name":"Retargeting","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C142816647","wikidata":"https://www.wikidata.org/wiki/Q5573018","display_name":"Glyph (data visualization)","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.25369998812675476},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.10237","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.10237","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,"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":"doi:10.48550/arxiv.2607.10237","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.10237","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5767396688461304,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"3D":[1,17],"scene":[2,42],"understanding":[3],"is":[4,107,171],"commonly":[5],"achieved":[6],"by":[7,232],"embedding":[8],"2D":[9],"vision-language":[10],"features":[11],"such":[12],"as":[13],"CLIP":[14],"into":[15,23],"a":[16,24,30,40,63,68,72,108,116,120,139,154,184],"Gaussian":[18],"Splatting":[19],"scene,":[20],"turning":[21],"it":[22,152],"text-queryable":[25],"semantic":[26,145],"field.":[27],"However,":[28],"attaching":[29],"high-dimensional":[31],"feature":[32,74],"to":[33,43,115,234,237],"each":[34,59],"of":[35,37,53,92,219],"millions":[36],"Gaussians":[38],"inflates":[39],"single":[41],"gigabytes,":[44],"which":[45,130],"makes":[46],"storage":[47,81,100,106,212],"and":[48,61,82,99,104,147,150,173,180,199,226],"deployment":[49],"the":[50,85,90,93,112,132,164,169,189,203,217,220,223],"real":[51],"bottleneck":[52],"these":[54],"fields.":[55],"Existing":[56],"compact":[57],"methods":[58],"learn":[60],"ship":[62],"per-scene":[64,136],"codec,":[65],"an":[66],"autoencoder,":[67],"quantized":[69],"codebook,":[70],"or":[71,215],"distilled":[73],"field,":[75],"entangling":[76],"field":[77,80,133,230],"construction":[78,98],"with":[79,153],"never":[83],"compressing":[84],"per-Gaussian":[86,113],"assignment":[87],"that":[88,97,105,159],"holds":[89],"bulk":[91],"cost.":[94],"We":[95,127],"argue":[96],"should":[101],"be":[102],"decoupled,":[103],"rate-distortion":[109],"problem":[110],"over":[111],"binding":[114,170],"small":[117],"anchor":[118],"table,":[119],"structure":[121],"no":[122,161,194],"prior":[123],"open-vocabulary":[124],"method":[125],"compresses.":[126],"present":[128],"CoSAG,":[129],"constructs":[131],"without":[134],"any":[135],"training":[137],"through":[138],"closed-form":[140],"transmittance-weighted":[141,178],"lift,":[142],"spatially":[143,155,167],"grounded":[144],"anchors,":[146],"multi-view":[148,181],"denoising,":[149],"stores":[151],"predictive":[156],"entropy":[157,190],"coder":[158,191],"ships":[160],"decoder.":[162],"Because":[163],"anchors":[165],"are":[166],"grounded,":[168],"predictable":[172],"therefore":[174],"highly":[175],"compressible.":[176],"The":[177],"lift":[179],"denoising":[182],"yield":[183],"clean,":[185],"view-consistent":[186],"assignment,":[187],"so":[188],"spends":[192],"almost":[193],"rate":[195],"on":[196],"correcting":[197],"noise":[198],"instead":[200],"codes":[201],"only":[202],"residual":[204],"against":[205],"its":[206],"spatial":[207],"prediction.":[208],"CoSAG":[209],"reaches":[210],"sub-megabyte":[211],"while":[213],"matching":[214],"exceeding":[216],"state":[218],"art":[221],"across":[222],"2D-rendered,":[224],"3D-selection,":[225],"dense-LSeg":[227],"protocols,":[228],"reducing":[229],"size":[231],"37":[233],"76x":[235],"relative":[236],"LangSplatV2":[238],"at":[239],"higher":[240],"accuracy.":[241]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-15T00:00:00"}