{"id":"https://openalex.org/W4414931207","doi":"https://doi.org/10.1109/iccv51701.2025.00898","title":"Details Matter for Indoor Open-Vocabulary 3D Instance Segmentation","display_name":"Details Matter for Indoor Open-Vocabulary 3D Instance Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414931207","doi":"https://doi.org/10.1109/iccv51701.2025.00898"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.23134","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101971881","display_name":"Sanghun Jung","orcid":"https://orcid.org/0000-0003-1302-0185"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sanghun Jung","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023908179","display_name":"Jingjing Zheng","orcid":"https://orcid.org/0000-0002-5728-9453"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingjing Zheng","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101760582","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0002-7244-8483"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Zhang","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110205627","display_name":"Nan Qiao","orcid":"https://orcid.org/0009-0003-2495-8109"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Qiao","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070952449","display_name":"Albert Y. C. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albert Y. C. Chen","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101720832","display_name":"Lu Xia","orcid":"https://orcid.org/0000-0002-0243-4975"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Xia","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705182","display_name":"Chi Liu","orcid":"https://orcid.org/0000-0002-2539-6916"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chi Liu","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102596172","display_name":"Yuyin Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuyin Sun","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Zeng","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025669663","display_name":"Hsiang-Wei Huang","orcid":"https://orcid.org/0009-0009-2474-8869"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsiang-Wei Huang","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110797782","display_name":"Byron Boots","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byron Boots","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102008600","display_name":"Min Sun","orcid":"https://orcid.org/0000-0001-9598-8178"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Sun","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105792706","display_name":"Cheng-Hao Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng-Hao Kuo","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5101971881"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3619662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9627","last_page":"9637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9596999883651733,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9596999883651733,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7242000102996826},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5662999749183655},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.5062000155448914},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4966999888420105},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4657999873161316},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43209999799728394},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4050000011920929},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.37139999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7391999959945679},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7242000102996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086000204086304},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5662999749183655},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4966999888420105},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.37139999866485596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3671000003814697},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.36169999837875366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33739998936653137},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.32820001244544983},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2865999937057495},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25519999861717224}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.23134","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.23134","pdf_url":"https://arxiv.org/pdf/2507.23134","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.23134","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.23134","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.23134","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.23134","pdf_url":"https://arxiv.org/pdf/2507.23134","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unlike":[0],"closed-vocabulary":[1,177],"3D":[2,11,22,83,92,98],"instance":[3,12,23,87],"segmentation":[4,13],"that":[5,39],"is":[6],"often":[7,15],"trained":[8],"end-to-end,":[9],"open-vocabulary":[10],"(OV-3DIS)":[14],"leverages":[16],"vision-language":[17],"models":[18],"(VLMs)":[19],"to":[20,65,73,96,129,146],"generate":[21,97],"proposals":[24,99,105],"and":[25,70,86,100,133,155,165,170],"classify":[26],"them.":[27],"While":[28],"various":[29],"concepts":[30,42,68],"have":[31],"been":[32],"proposed":[33],"from":[34],"existing":[35],"research,":[36],"we":[37,52,113,138],"observe":[38],"these":[40],"individual":[41],"are":[43],"not":[44],"mutually":[45],"exclusive":[46],"but":[47],"complementary.":[48],"In":[49],"this":[50],"paper,":[51],"propose":[53],"a":[54,63],"new":[55],"state-of-the-art":[56,161],"solution":[57,78],"for":[58],"OV-3DIS":[59],"by":[60,106],"carefully":[61],"designing":[62],"recipe":[64],"combine":[66],"the":[67,80,110,115,140],"together":[69],"refining":[71],"them":[72],"address":[74],"key":[75],"challenges.":[76],"Our":[77,158],"follows":[79],"two-stage":[81],"scheme:":[82],"proposal":[84,94],"generation":[85],"classification.":[88],"We":[89],"employ":[90],"robust":[91],"tracking-based":[93],"aggregation":[95],"remove":[101],"overlapped":[102],"or":[103],"partial":[104],"iterative":[107],"merging/removal.":[108],"For":[109],"classification":[111],"stage,":[112],"replace":[114],"standard":[116],"CLIP":[117],"model":[118],"with":[119],"Alpha-CLIP,":[120],"which":[121],"incorporates":[122],"object":[123],"masks":[124],"as":[125],"an":[126,175],"alpha":[127],"channel":[128],"reduce":[130],"background":[131],"noise":[132],"obtain":[134],"object-centric":[135],"representation.":[136],"Additionally,":[137],"introduce":[139],"standardized":[141],"maximum":[142],"similarity":[143],"(SMS)":[144],"score":[145],"normalize":[147],"text-to-proposal":[148],"similarity,":[149],"effectively":[150],"filtering":[151],"out":[152],"false":[153],"positives":[154],"boosting":[156],"precision.":[157],"framework":[159],"achieves":[160],"performance":[162],"on":[163],"ScanNet200":[164],"S3DIS":[166],"across":[167],"all":[168],"AP":[169],"AR":[171],"metrics,":[172],"even":[173],"surpassing":[174],"end-to-end":[176],"method.":[178]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}