{"id":"https://openalex.org/W4416748203","doi":"https://doi.org/10.1109/iros60139.2025.11247182","title":"OpenFusion++: An Open-vocabulary Real-time Scene Understanding System","display_name":"OpenFusion++: An Open-vocabulary Real-time Scene Understanding System","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748203","doi":"https://doi.org/10.1109/iros60139.2025.11247182"},"language":"en","primary_location":{"id":"doi:10.1109/iros60139.2025.11247182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247182","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11311/1302489","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060328206","display_name":"Xiaofeng Jin","orcid":"https://orcid.org/0000-0002-1804-5456"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Xiaofeng Jin","raw_affiliation_strings":["Politecnico di Milano,Milan,Italy,20133"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milan,Italy,20133","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008765839","display_name":"Matteo Frosi","orcid":"https://orcid.org/0000-0002-5936-7945"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Frosi","raw_affiliation_strings":["Politecnico di Milano,Milan,Italy,20133"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milan,Italy,20133","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003932703","display_name":"Matteo Matteucci","orcid":"https://orcid.org/0000-0002-8306-6739"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Matteucci","raw_affiliation_strings":["Politecnico di Milano,Milan,Italy,20133"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milan,Italy,20133","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060328206"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39985509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"634","last_page":"641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5027999877929688,"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":0.5027999877929688,"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":0.18649999797344208,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.052299998700618744,"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/object","display_name":"Object (grammar)","score":0.5787000060081482},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5076000094413757},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5005000233650208},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.48420000076293945},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.40310001373291016},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3971000015735626},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3944999873638153},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.37770000100135803},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.3767000138759613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824400007724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6057999730110168},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5005000233650208},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.37770000100135803},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35670000314712524},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31619998812675476},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2948000133037567},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros60139.2025.11247182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247182","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"},{"id":"pmh:oai:re.public.polimi.it:11311/1302489","is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1302489","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:re.public.polimi.it:11311/1302489","is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1302489","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2058535340","https://openalex.org/W2594519801","https://openalex.org/W3159481202","https://openalex.org/W4312980231","https://openalex.org/W4313156423","https://openalex.org/W4385318467","https://openalex.org/W4385431115","https://openalex.org/W4386065742","https://openalex.org/W4390873101","https://openalex.org/W4390874575","https://openalex.org/W4401417460","https://openalex.org/W4402704512","https://openalex.org/W4402733570","https://openalex.org/W4402753899","https://openalex.org/W4403906550","https://openalex.org/W4409262271","https://openalex.org/W4413925062"],"related_works":[],"abstract_inverted_index":{"Real-time":[0],"open-vocabulary":[1],"scene":[2],"understanding":[3],"is":[4],"essential":[5],"for":[6,91],"efficient":[7],"3D":[8,48,55],"perception":[9],"in":[10,111],"applications":[11],"such":[12],"as":[13],"vision-language":[14],"navigation,":[15],"embodied":[16],"intelligence,":[17],"and":[18,32,78,101,115],"augmented":[19],"reality.":[20],"However,":[21],"existing":[22],"methods":[23],"suffer":[24],"from":[25,62],"imprecise":[26],"instance":[27,76],"segmentation,":[28],"static":[29],"semantic":[30,68,113],"updates,":[31],"limited":[33],"handling":[34],"of":[35],"complex":[36],"queries.":[37],"To":[38],"address":[39],"these":[40],"issues,":[41],"we":[42],"present":[43],"OpenFusion++,":[44],"a":[45,80],"TSDF-based":[46],"real-time":[47],"semantic-geometric":[49],"reconstruction":[50],"system.":[51],"Our":[52],"approach":[53],"refines":[54],"point":[56],"clouds":[57],"by":[58],"fusing":[59],"confidence":[60],"maps":[61],"foundational":[63],"models,":[64],"dynamically":[65],"updates":[66],"global":[67],"labels":[69],"via":[70],"an":[71],"adaptive":[72],"cache":[73],"based":[74],"on":[75,96],"area,":[77],"employs":[79],"dual-path":[81],"encoding":[82],"framework":[83],"that":[84,105],"integrates":[85],"object":[86],"attributes":[87],"with":[88],"environmental":[89],"context":[90],"precise":[92],"query":[93,116],"responses.":[94],"Experiments":[95],"the":[97,109],"ICL,":[98],"Replica,":[99],"ScanNet,":[100],"ScanNet++":[102],"datasets":[103],"demonstrate":[104],"OpenFusion++":[106],"significantly":[107],"outperforms":[108],"baseline":[110],"both":[112],"accuracy":[114],"responsiveness.":[117]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}