{"id":"https://openalex.org/W4416749043","doi":"https://doi.org/10.1109/iros60139.2025.11246404","title":"OVSG-SLAM: Open-Vocabulary Semantic Gaussian Splatting SLAM","display_name":"OVSG-SLAM: Open-Vocabulary Semantic Gaussian Splatting SLAM","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749043","doi":"https://doi.org/10.1109/iros60139.2025.11246404"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246404","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/A5066553810","display_name":"Ziyan Liu","orcid":"https://orcid.org/0009-0005-5370-0849"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhehang Liu","raw_affiliation_strings":["Shenzhen MSU-BIT University,Guangdong Laboratory of Machine Perception and Intelligent Computing,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University,Guangdong Laboratory of Machine Perception and Intelligent Computing,Shenzhen,China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101947008","display_name":"Shishen Li","orcid":"https://orcid.org/0009-0008-5565-7196"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shishen Li","raw_affiliation_strings":["Shenzhen MSU-BIT University,Guangdong Laboratory of Machine Perception and Intelligent Computing,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University,Guangdong Laboratory of Machine Perception and Intelligent Computing,Shenzhen,China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083191742","display_name":"Guichen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guichen Huang","raw_affiliation_strings":["Shenzhen MSU-BIT University,Guangdong Laboratory of Machine Perception and Intelligent Computing,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University,Guangdong Laboratory of Machine Perception and Intelligent Computing,Shenzhen,China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4388482657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071656520","display_name":"Yuwei Wu","orcid":"https://orcid.org/0000-0001-6300-6336"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Wu","raw_affiliation_strings":["Shenzhen MSU-BIT University,Guangdong Laboratory of Machine Perception and Intelligent Computing,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University,Guangdong Laboratory of Machine Perception and Intelligent Computing,Shenzhen,China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4388482657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"12804","last_page":"12811"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.8148999810218811,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.8148999810218811,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09780000150203705,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.016100000590085983,"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":0.5411999821662903},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.49459999799728394},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.48420000076293945},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4733999967575073},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4480000138282776},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.41749998927116394},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4088999927043915},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.39089998602867126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807699978351593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6177999973297119},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48969998955726624},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.37229999899864197},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C86369673","wikidata":"https://www.wikidata.org/wiki/Q1203659","display_name":"Simultaneous localization and mapping","level":4,"score":0.30889999866485596},{"id":"https://openalex.org/C149106765","wikidata":"https://www.wikidata.org/wiki/Q1982453","display_name":"Denotation (semiotics)","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246404","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1612997784","https://openalex.org/W2033979122","https://openalex.org/W2097696373","https://openalex.org/W2250172176","https://openalex.org/W2594519801","https://openalex.org/W2745859992","https://openalex.org/W2888144883","https://openalex.org/W2963706662","https://openalex.org/W3004300126","https://openalex.org/W3090386798","https://openalex.org/W3201048198","https://openalex.org/W4367663104","https://openalex.org/W4385318467","https://openalex.org/W4385430678","https://openalex.org/W4385431115","https://openalex.org/W4390874575","https://openalex.org/W4392970266","https://openalex.org/W4401414715","https://openalex.org/W4401416305","https://openalex.org/W4401691722","https://openalex.org/W4402354022","https://openalex.org/W4402389384","https://openalex.org/W4402698355","https://openalex.org/W4402716032","https://openalex.org/W4402727055","https://openalex.org/W4402727529","https://openalex.org/W4402727597","https://openalex.org/W4402727846","https://openalex.org/W4402771875","https://openalex.org/W4403770187","https://openalex.org/W4403792110","https://openalex.org/W4405785039"],"related_works":[],"abstract_inverted_index":{"Most":[0],"conventional":[1],"semantic":[2,9,17,45,90,122,130,163],"SLAM":[3,31,46,91],"approaches":[4],"concentrate":[5],"on":[6,15,75,144],"maintaining":[7],"3D":[8,40,89,162],"consistency":[10],"while":[11,119],"overlooking":[12],"their":[13],"reliance":[14,74],"predefined":[16,76],"categories,":[18],"ultimately":[19],"limiting":[20],"flexibility":[21],"in":[22,158],"scene":[23,59,135],"understanding.":[24],"We":[25],"propose":[26],"Open-Vocabulary":[27],"Semantic":[28],"Gaussian":[29,41],"Splatting":[30],"(OVSG-SLAM),":[32],"an":[33,138],"approach":[34],"that":[35,151],"integrates":[36],"multi-modal":[37],"perception":[38],"and":[39,98,147,161],"splatting":[42],"into":[43],"a":[44,107,128],"framework.":[47],"By":[48],"combining":[49],"the":[50,62,73,134,145,152],"advantages":[51],"of":[52,67,126],"Segment":[53],"Anything":[54],"(SAM)":[55],"for":[56],"open-vocabulary":[57,84],"2D":[58],"understanding":[60],"with":[61,88],"powerful":[63],"feature":[64,108],"extraction":[65],"capabilities":[66],"vision-language":[68],"models,":[69],"our":[70],"method":[71,154],"eliminates":[72],"closed-set":[77],"categories.":[78],"Although":[79],"Vision-Language":[80],"Models":[81],"(VLMs)":[82],"provide":[83],"reasoning,":[85],"integrating":[86],"them":[87],"poses":[92],"challenges":[93],"such":[94],"as":[95],"embedding":[96,109],"ambiguity":[97],"computational":[99,117],"overhead.":[100],"To":[101],"address":[102],"these":[103],"challenges,":[104],"we":[105,132],"present":[106],"strategy":[110],"called":[111],"differentiable":[112],"identity-aware":[113],"encoding,":[114],"which":[115],"reduces":[116],"cost":[118],"ensuring":[120],"accurate":[121],"mapping.":[123],"Furthermore,":[124],"instead":[125],"using":[127],"traditional":[129],"loss,":[131],"optimize":[133],"representation":[136],"through":[137],"identity":[139],"loss.":[140],"Extensive":[141],"experimental":[142],"evaluations":[143],"Replica":[146],"ScanNet":[148],"datasets":[149],"demonstrate":[150],"proposed":[153],"achieves":[155],"state-of-the-art":[156],"performance":[157],"mapping,":[159],"tracking":[160],"segmentation":[164],"tasks.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}