{"id":"https://openalex.org/W7139120481","doi":"https://doi.org/10.48550/arxiv.2603.16103","title":"NanoGS: Training-Free Gaussian Splat Simplification","display_name":"NanoGS: Training-Free Gaussian Splat Simplification","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7139120481","doi":"https://doi.org/10.48550/arxiv.2603.16103"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.16103","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16103","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.16103","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114082883","display_name":"Butian Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiong, Butian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129802914","display_name":"Rong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Rong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129775321","display_name":"Tiantian Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Tiantian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068509275","display_name":"Meida Chen","orcid":"https://orcid.org/0000-0002-2436-3848"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Meida","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130022253","display_name":"Zhiwen Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Zhiwen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066604966","display_name":"Andrew Feng","orcid":"https://orcid.org/0000-0002-1675-745X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Andrew","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114082883"],"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.7319999933242798,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.7319999933242798,"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":0.11469999700784683,"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/T11019","display_name":"Image Enhancement Techniques","score":0.09610000252723694,"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/gaussian","display_name":"Gaussian","score":0.7163000106811523},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.7052000164985657},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6972000002861023},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5153999924659729},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.48649999499320984},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.3357999920845032}],"concepts":[{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.7163000106811523},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7052000164985657},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6972000002861023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6184999942779541},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5184000134468079},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5153999924659729},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C140086265","wikidata":"https://www.wikidata.org/wiki/Q11341754","display_name":"Merge algorithm","level":4,"score":0.30889999866485596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29829999804496765},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.296999990940094},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C7218915","wikidata":"https://www.wikidata.org/wiki/Q1054475","display_name":"Gaussian function","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.16103","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16103","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.16103","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16103","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.48813092708587646,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0],"Gaussian":[1,55,124,137,177],"Splat":[2,56,138,178],"(3DGS)":[3],"enables":[4],"high-fidelity,":[5],"real-time":[6],"novel":[7],"view":[8],"synthesis":[9],"by":[10],"representing":[11],"scenes":[12],"with":[13,40,84,153],"large":[14],"sets":[15],"of":[16,23,59,82],"anisotropic":[17],"primitives,":[18],"but":[19],"often":[20],"requires":[21],"millions":[22],"Splats,":[24],"incurring":[25],"significant":[26],"storage":[27],"and":[28,51,93,106,116,130,144,173],"transmission":[29],"costs.":[30],"Most":[31],"existing":[32,136,154],"compression":[33],"methods":[34],"rely":[35],"on":[36,61,135,142],"GPU-intensive":[37],"post-training":[38],"optimization":[39],"calibrated":[41],"images,":[42],"limiting":[43],"practical":[44,174],"deployment.":[45],"We":[46],"introduce":[47],"NanoGS,":[48],"a":[49,73,80,85,98],"training-free":[50],"lightweight":[52],"framework":[53],"for":[54,176],"simplification.":[57,179],"Instead":[58],"relying":[60],"image-based":[62],"rendering":[63,155,168],"supervision,":[64],"NanoGS":[65,121,132,160],"formulates":[66],"simplification":[67],"as":[68],"local":[69,114],"pairwise":[70],"merging":[71],"over":[72],"sparse":[74],"spatial":[75],"graph.":[76],"The":[77],"method":[78],"approximates":[79],"pair":[81],"Gaussians":[83],"single":[86],"primitive":[87,163],"using":[88],"mass":[89],"preserved":[90],"moment":[91],"matching":[92],"evaluates":[94],"merge":[95,100,111],"quality":[96],"through":[97],"principled":[99],"cost":[101],"between":[102],"the":[103,146],"original":[104],"mixture":[105],"its":[107],"approximation.":[108],"By":[109],"restricting":[110],"candidates":[112],"to":[113],"neighborhoods":[115],"selecting":[117],"compatible":[118],"pairs":[119],"efficiently,":[120],"produces":[122],"compact":[123],"representations":[125],"while":[126,165],"preserving":[127],"scene":[128],"structure":[129],"appearance.":[131],"operates":[133],"directly":[134],"models,":[139],"runs":[140],"efficiently":[141],"CPU,":[143],"preserves":[145],"standard":[147],"3DGS":[148],"parameterization,":[149],"enabling":[150],"seamless":[151],"integration":[152],"pipelines.":[156],"Experiments":[157],"demonstrate":[158],"that":[159],"substantially":[161],"reduces":[162],"count":[164],"maintaining":[166],"high":[167],"fidelity,":[169],"providing":[170],"an":[171],"efficient":[172],"solution":[175],"Our":[180],"project":[181],"website":[182],"is":[183],"available":[184],"at":[185],"https://saliteta.github.io/NanoGS/.":[186]},"counts_by_year":[],"updated_date":"2026-03-20T20:54:20.808490","created_date":"2026-03-20T00:00:00"}