{"id":"https://openalex.org/W4416750577","doi":"https://doi.org/10.1109/iros60139.2025.11246515","title":"GaussianGraph: 3D Gaussian-Based Scene Graph Generation for Open-World Scene Understanding","display_name":"GaussianGraph: 3D Gaussian-Based Scene Graph Generation for Open-World Scene Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750577","doi":"https://doi.org/10.1109/iros60139.2025.11246515"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5015493248","display_name":"Xihan Wang","orcid":"https://orcid.org/0009-0009-7570-3978"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihan Wang","raw_affiliation_strings":["Beijing Institute of Technology,School of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Automation,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033935836","display_name":"Dianyi Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dianyi Yang","raw_affiliation_strings":["Beijing Institute of Technology,School of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Automation,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102012590","display_name":"Yu Gao","orcid":"https://orcid.org/0000-0001-7459-185X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gao","raw_affiliation_strings":["Beijing Institute of Technology,School of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Automation,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068949782","display_name":"Yufeng Yue","orcid":"https://orcid.org/0000-0001-6628-7946"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Yue","raw_affiliation_strings":["Beijing Institute of Technology,School of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Automation,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105111708","display_name":"Yi Yang","orcid":"https://orcid.org/0009-0008-0117-8181"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Beijing Institute of Technology,School of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Automation,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091459774","display_name":"Mengyin Fu","orcid":"https://orcid.org/0000-0002-5520-7127"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyin Fu","raw_affiliation_strings":["Beijing Institute of Technology,School of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Automation,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4091","last_page":"4098"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8373000025749207,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8373000025749207,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.031300000846385956,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.026599999517202377,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/segmentation","display_name":"Segmentation","score":0.6189000010490417},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5605000257492065},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4706999957561493},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4684999883174896},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4528999924659729},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4431000053882599},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.412200003862381},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3903999924659729},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3833000063896179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7836999893188477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6686000227928162},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6189000010490417},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5605000257492065},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4943000078201294},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.412200003862381},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3903999924659729},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3774999976158142},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.2711000144481659},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2160821342","https://openalex.org/W2563408008","https://openalex.org/W2594519801","https://openalex.org/W2886970679","https://openalex.org/W2963184176","https://openalex.org/W3095974555","https://openalex.org/W4231029117","https://openalex.org/W4312744661","https://openalex.org/W4385318467","https://openalex.org/W4385431115","https://openalex.org/W4386065742","https://openalex.org/W4386066076","https://openalex.org/W4386324448","https://openalex.org/W4389665630","https://openalex.org/W4390872744","https://openalex.org/W4390874575","https://openalex.org/W4390874670","https://openalex.org/W4401414715","https://openalex.org/W4401417460","https://openalex.org/W4401691722","https://openalex.org/W4402354022","https://openalex.org/W4402716032","https://openalex.org/W4402716083","https://openalex.org/W4402727529","https://openalex.org/W4402727764","https://openalex.org/W4402771875","https://openalex.org/W4402917081","https://openalex.org/W4403677113","https://openalex.org/W4404002612","https://openalex.org/W4404612908","https://openalex.org/W4409346685","https://openalex.org/W4413917118"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,113,145],"3D":[3,33,118],"Gaussian":[4],"Splatting(3DGS)":[5],"have":[6],"significantly":[7,89],"improved":[8],"semantic":[9,64,147],"scene":[10,59,67,80,96,131,159],"understanding,":[11],"enabling":[12],"natural":[13],"language":[14],"queries":[15],"to":[16,32,79],"localize":[17],"objects":[18],"within":[19],"a":[20,53,72,154],"scene.":[21],"However,":[22],"existing":[23],"methods":[24,144],"primarily":[25],"focus":[26],"on":[27,136],"embedding":[28],"compressed":[29],"CLIP":[30],"features":[31],"Gaussians,":[34],"suffering":[35],"from":[36,106],"low":[37],"object":[38,100,150],"segmentation":[39,91,148],"accuracy":[40],"and":[41,66,82,88,102,149,161,167],"lack":[42],"spatial":[43,103,114,126],"reasoning":[44],"capabilities.":[45],"To":[46,110],"address":[47,111],"these":[48],"limitations,":[49],"we":[50,94,116],"propose":[51,117],"GaussianGraph,":[52],"novel":[54],"framework":[55],"that":[56,121,140],"enhances":[57],"3DGS-based":[58],"understanding":[60,160],"by":[61,98],"integrating":[62,99],"adaptive":[63],"clustering":[65,74],"graph":[68,132],"generation.":[69],"We":[70,163],"introduce":[71],"\u2018Control-Follow\u2019":[73],"strategy,":[75],"which":[76],"dynamically":[77],"adapts":[78],"scale":[81],"feature":[83,86],"distribution,":[84],"avoiding":[85],"compression":[87],"improving":[90],"accuracy.":[92],"Additionally,":[93],"enrich":[95],"representation":[97],"attributes":[101],"relations":[104,124],"extracted":[105],"2D":[107],"foundation":[108],"models.":[109],"inaccuracies":[112],"relationships,":[115],"correction":[119],"modules":[120],"filter":[122],"implausible":[123],"through":[125],"consistency":[127],"verification,":[128],"ensuring":[129],"reliable":[130],"construction.":[133],"Extensive":[134],"experiments":[135],"three":[137],"datasets":[138],"demonstrate":[139],"GaussianGraph":[141],"outperforms":[142],"state-of-the-art":[143],"both":[146],"grounding":[151],"tasks,":[152],"providing":[153],"robust":[155],"solution":[156],"for":[157],"complex":[158],"interaction.":[162],"provide":[164],"supplementary":[165],"video":[166],"code":[168],"at":[169],"https://wangxihan-bit.github.io/GaussianGraph.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}