{"id":"https://openalex.org/W4415540452","doi":"https://doi.org/10.1145/3746027.3755146","title":"Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs","display_name":"Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540452","doi":"https://doi.org/10.1145/3746027.3755146"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755146","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101368872","display_name":"Shaohui Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohui Dai","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0005-4139-7950","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102898975","display_name":"Yansong Qu","orcid":"https://orcid.org/0009-0003-4325-6858"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yansong Qu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0003-4325-6858","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zheyan Li","orcid":"https://orcid.org/0009-0001-9142-8197"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheyan Li","raw_affiliation_strings":["Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0001-9142-8197","affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602137","display_name":"Xinyang Li","orcid":"https://orcid.org/0000-0002-2932-8953"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyang Li","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0002-2932-8953","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073570293","display_name":"Shengchuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchuan Zhang","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0002-0800-0609","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014628588","display_name":"Liujuan Cao","orcid":"https://orcid.org/0000-0002-7645-9606"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liujuan Cao","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0002-7645-9606","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3303976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3673","last_page":"3682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9973999857902527,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9973999857902527,"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":0.996399998664856,"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":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5259000062942505},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5257999897003174},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5202999711036682},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4846000075340271},{"id":"https://openalex.org/keywords/cut","display_name":"Cut","score":0.44029998779296875},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.42160001397132874},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41359999775886536},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4083999991416931},{"id":"https://openalex.org/keywords/reprojection-error","display_name":"Reprojection error","score":0.37880000472068787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770799994468689},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5259000062942505},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48980000615119934},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C5134670","wikidata":"https://www.wikidata.org/wiki/Q1626444","display_name":"Cut","level":4,"score":0.44029998779296875},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41359999775886536},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38679999113082886},{"id":"https://openalex.org/C23903533","wikidata":"https://www.wikidata.org/wiki/Q17122739","display_name":"Reprojection error","level":3,"score":0.37880000472068787},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.3693999946117401},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35929998755455017},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2689000070095062},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755146","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2195152090","display_name":null,"funder_award_id":"U21B2037,U22B2051,U23A20383,U21A20472,62176222,62176223,62176226,62072386,62072387,62072389,62002305,62272401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6075090814","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2118246710","https://openalex.org/W2346698422","https://openalex.org/W2594519801","https://openalex.org/W2955873422","https://openalex.org/W2963281829","https://openalex.org/W3187482491","https://openalex.org/W3215769467","https://openalex.org/W4200150166","https://openalex.org/W4214704440","https://openalex.org/W4380723689","https://openalex.org/W4385318467","https://openalex.org/W4390872744","https://openalex.org/W4393248012","https://openalex.org/W4402704512","https://openalex.org/W4402704609","https://openalex.org/W4402715888","https://openalex.org/W4402715988","https://openalex.org/W4402716032","https://openalex.org/W4402716405","https://openalex.org/W4402727529","https://openalex.org/W4402727541","https://openalex.org/W4402733574","https://openalex.org/W4402754045","https://openalex.org/W4402771875"],"related_works":[],"abstract_inverted_index":{"Bridging":[0],"natural":[1],"language":[2],"and":[3,26,94,102,142,150],"3D":[4,19,63,100,139],"geometry":[5],"is":[6],"a":[7,73,78,104,155],"crucial":[8],"step":[9],"toward":[10],"flexible,":[11],"language-driven":[12],"scene":[13,28,90],"understanding.":[14,109],"While":[15],"recent":[16],"advances":[17],"in":[18,56],"Gaussian":[20,83],"Splatting":[21],"(3DGS)":[22],"have":[23],"enabled":[24],"fast":[25],"high-quality":[27],"reconstruction,":[29],"research":[30],"has":[31],"also":[32,59],"explored":[33],"incorporating":[34],"open-vocabulary":[35,108,152,167],"understanding":[36],"into":[37,91],"3DGS.":[38],"However,":[39],"most":[40],"existing":[41],"methods":[42],"require":[43],"iterative":[44,132],"optimization":[45],"over":[46,175],"per-view":[47],"2D":[48,123],"semantic":[49,124,140,157,171],"feature":[50],"maps,":[51],"which":[52],"not":[53],"only":[54],"results":[55],"inefficiencies":[57],"but":[58],"leads":[60],"to":[61],"inconsistent":[62],"semantics":[64],"across":[65],"views.":[66],"To":[67],"address":[68],"these":[69],"limitations,":[70],"we":[71,115],"introduce":[72],"training-free":[74],"framework":[75],"that":[76,121,162],"constructs":[77],"superpoint":[79,86],"graph":[80,87,113],"directly":[81],"from":[82],"primitives.":[84],"The":[85,134],"partitions":[88],"the":[89,112,127],"spatially":[92],"compact":[93],"semantically":[95],"coherent":[96],"regions,":[97],"forming":[98],"view-consistent":[99],"entities":[101],"providing":[103],"structured":[105],"foundation":[106],"for":[107],"Based":[110],"on":[111],"structure,":[114],"design":[116],"an":[117],"efficient":[118],"reprojection":[119],"strategy":[120],"lifts":[122],"features":[125],"onto":[126],"superpoints,":[128],"avoiding":[129],"costly":[130],"multi-view":[131],"training.":[133],"resulting":[135],"representation":[136],"ensures":[137],"strong":[138],"coherence":[141],"naturally":[143],"supports":[144],"hierarchical":[145],"understanding,":[146],"enabling":[147],"both":[148],"coarse-":[149],"fine-grained":[151],"perception":[153],"within":[154],"unified":[156],"field.":[158],"Extensive":[159],"experiments":[160],"demonstrate":[161],"our":[163],"method":[164],"achieves":[165],"state-of-the-art":[166],"segmentation":[168],"performance,":[169],"with":[170],"field":[172],"reconstruction":[173],"completed":[174],"30\u00d7":[176],"faster.":[177]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-25T00:00:00"}