{"id":"https://openalex.org/W7224123307","doi":"https://doi.org/10.48550/arxiv.2610.36462","title":"ClusterSplat: Semantic Cluster Selection for 3D Visual Grounding in Gaussian Splatting","display_name":"ClusterSplat: Semantic Cluster Selection for 3D Visual Grounding in Gaussian Splatting","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224123307","doi":"https://doi.org/10.48550/arxiv.2610.36462"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.36462","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36462","pdf_url":"https://arxiv.org/pdf/2610.36462","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.36462","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160021625","display_name":"Jaesung Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Jaesung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125212802","display_name":"Hyeontaek Hwang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hwang, Hyeontaek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144008315","display_name":"Gabriel Manalu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manalu, Gabriel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160023996","display_name":"Daeyoung Kim","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Daeyoung","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":true,"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":0.9775000214576721,"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":0.9775000214576721,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.007199999876320362,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/3d-visual-grounding","display_name":"3D visual grounding","score":0.9710000157356262},{"id":"https://openalex.org/keywords/3d-gaussian-splatting","display_name":"3D Gaussian Splatting","score":0.7910000085830688},{"id":"https://openalex.org/keywords/referring-expressions","display_name":"referring expressions","score":0.7929999828338623},{"id":"https://openalex.org/keywords/3d-shape-retrieval","display_name":"3D model retrieval","score":0.574999988079071},{"id":"https://openalex.org/keywords/scanrefer","display_name":"ScanRefer","score":0.6159999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871999740600586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6998999714851379},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6140000224113464},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5654000043869019},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5281000137329102},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C2776863239","wikidata":"https://www.wikidata.org/wiki/Q7936601","display_name":"Visual hull","level":3,"score":0.48669999837875366},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.4796000123023987},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4237000048160553},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C58103923","wikidata":"https://www.wikidata.org/wiki/Q2286025","display_name":"Silhouette","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.36462","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36462","pdf_url":"https://arxiv.org/pdf/2610.36462","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.36462","doi":"https://doi.org/10.48550/arxiv.2610.36462","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.36462","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.36462","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36462","pdf_url":"https://arxiv.org/pdf/2610.36462","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224123307.pdf","grobid_xml":"https://content.openalex.org/works/W7224123307.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7170051605","https://openalex.org/W7166722272","https://openalex.org/W7203665098","https://openalex.org/W7172093371","https://openalex.org/W7169679773","https://openalex.org/W4416551492","https://openalex.org/W7166841041","https://openalex.org/W7197039040","https://openalex.org/W7216319301","https://openalex.org/W4416243673"],"abstract_inverted_index":{"We":[0],"study":[1],"3D":[2,6,30,36,74,135,158,198,204],"visual":[3],"grounding":[4],"in":[5],"Gaussian":[7,88],"Splatting":[8],"(3DGS),":[9],"where":[10],"a":[11,16,21,26,100,105,112,115,124],"referring":[12,113,180],"expression":[13],"should":[14],"identify":[15],"target":[17,75,136,159],"object":[18],"as":[19,77],"both":[20],"rendered":[22,142,153,192],"2D":[23,145,154,193],"mask":[24],"and":[25,58,64,94,127,156,195],"set":[27,107],"of":[28,108],"explicit":[29,134,157],"Gaussians.":[31],"Prior":[32],"methods":[33],"typically":[34],"extract":[35],"targets":[37],"by":[38,72],"applying":[39],"heuristic":[40],"thresholding":[41],"or":[42],"top-ratio":[43],"filtering":[44],"to":[45,66],"dense":[46],"primitive-level":[47],"relevance":[48],"scores.":[49],"However,":[50],"these":[51],"scores":[52],"often":[53],"vary":[54],"substantially":[55],"across":[56],"scenes":[57],"prompts,":[59],"making":[60],"such":[61],"heuristics":[62],"sensitive":[63],"leading":[65],"unstable":[67],"targeting.":[68],"ClusterSplat":[69,149,188],"addresses":[70],"this":[71],"reframing":[73],"selection":[76,79],"cluster-level":[78],"over":[80],"scene-adaptive":[81],"candidates.":[82,110],"The":[83],"method":[84],"first":[85],"learns":[86],"instance-aware":[87],"features,":[89],"forms":[90],"feature-aware":[91],"seed":[92,97],"voxels,":[93],"merges":[95],"neighboring":[96],"voxels":[98],"when":[99],"description-length":[101],"criterion":[102],"decreases,":[103],"producing":[104],"scene-specific":[106],"cluster":[109,117,121,130,139],"Given":[111],"expression,":[114],"query-conditioned":[116],"scorer":[118],"ranks":[119],"the":[120,128,133,144,151,162,169,175,190,196],"candidates":[122],"with":[123],"lightweight":[125],"MLP,":[126],"selected":[129],"directly":[131],"defines":[132],"while":[137,201],"its":[138],"score":[140],"is":[141,209],"for":[143],"mask.":[146],"On":[147,182],"ScanRefer,":[148],"achieves":[150,189],"best":[152,170],"segmentation":[155],"metrics":[160],"among":[161],"compared":[163],"3DGS":[164],"baselines.":[165],"It":[166],"also":[167],"obtains":[168],"average":[171],"Ref-LERF":[172],"scores,":[173],"supporting":[174],"same":[176],"trend":[177],"under":[178],"fine-grained":[179],"descriptions.":[181],"ScanNet":[183],"v2":[184],"class":[185],"name":[186],"queries,":[187],"strongest":[191],"results":[194],"highest":[197],"matching":[199],"accuracy,":[200],"maintaining":[202],"competitive":[203],"IoU.":[205],"Our":[206],"project":[207],"page":[208],"available":[210],"at":[211],"https://jaesung8.github.io/clustersplat/":[212],".":[213]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-29T00:00:00"}