{"id":"https://openalex.org/W4413558875","doi":"https://doi.org/10.1109/3dv66043.2025.00114","title":"Vocabulary-Free 3D Instance Segmentation with Vision-Language Assistant","display_name":"Vocabulary-Free 3D Instance Segmentation with Vision-Language Assistant","publication_year":2025,"publication_date":"2025-03-25","ids":{"openalex":"https://openalex.org/W4413558875","doi":"https://doi.org/10.1109/3dv66043.2025.00114"},"language":"en","primary_location":{"id":"doi:10.1109/3dv66043.2025.00114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv66043.2025.00114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},"type":"article","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/A5014616639","display_name":"Guofeng Mei","orcid":"https://orcid.org/0000-0002-0494-5031"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Guofeng Mei","raw_affiliation_strings":["Fondazione Bruno Kessler,Trento,Italy,38123"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Trento,Italy,38123","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007354971","display_name":"Luigi Riz","orcid":"https://orcid.org/0009-0000-4687-4297"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luigi Riz","raw_affiliation_strings":["Fondazione Bruno Kessler,Trento,Italy,38123"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Trento,Italy,38123","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377935","display_name":"Yiming Wang","orcid":"https://orcid.org/0000-0002-5932-4371"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Yiming Wang","raw_affiliation_strings":["Fondazione Bruno Kessler,Trento,Italy,38123"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Trento,Italy,38123","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067244774","display_name":"Fabio Poiesi","orcid":"https://orcid.org/0000-0002-9769-1279"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Poiesi","raw_affiliation_strings":["Fondazione Bruno Kessler,Trento,Italy,38123"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Trento,Italy,38123","institution_ids":["https://openalex.org/I2277624104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2277624104"],"apc_list":null,"apc_paid":null,"fwci":1.7646,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86553305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1197","last_page":"1210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9890000224113464,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9890000224113464,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9868000149726868,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9835000038146973,"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/computer-science","display_name":"Computer science","score":0.7485738396644592},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6324109435081482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6064415574073792},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5472887754440308},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5273697376251221},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4653312563896179},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4292331039905548},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3676837086677551},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.25405436754226685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485738396644592},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6324109435081482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6064415574073792},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5472887754440308},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5273697376251221},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4653312563896179},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4292331039905548},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3676837086677551},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25405436754226685},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/3dv66043.2025.00114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv66043.2025.00114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1999478155","https://openalex.org/W2460657278","https://openalex.org/W2594519801","https://openalex.org/W4214773923","https://openalex.org/W4221154304","https://openalex.org/W4312274934","https://openalex.org/W4312424618","https://openalex.org/W4312649925","https://openalex.org/W4312912313","https://openalex.org/W4383109105","https://openalex.org/W4385431115","https://openalex.org/W4386065742","https://openalex.org/W4386066076","https://openalex.org/W4386071493","https://openalex.org/W4386075561","https://openalex.org/W4390874575","https://openalex.org/W4399410938","https://openalex.org/W4402704512","https://openalex.org/W4402726938","https://openalex.org/W4402727764","https://openalex.org/W4402727846","https://openalex.org/W4402733574","https://openalex.org/W4402753560","https://openalex.org/W4402774479","https://openalex.org/W4402917081"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W3167549738","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Most":[0],"recent":[1],"3D":[2,63,107,125],"instance":[3,64,93,108,126,153],"segmentation":[4,65],"methods":[5,165],"are":[6,18,121,147],"open":[7],"vocabulary,":[8,30],"offering":[9],"a":[10,23,67,77,82,130],"greater":[11],"flexibility":[12],"than":[13],"closedvocabulary":[14],"methods.":[15],"Yet,":[16],"they":[17],"limited":[19],"to":[20,61,95],"reasoning":[21],"within":[22],"specific":[24],"set":[25],"of":[26,72],"concepts,":[27],"i.e.,":[28,48],"the":[29,33,51,54,58,102,113,150],"prompted":[31],"by":[32],"user":[34],"at":[35],"test":[36],"time.":[37],"In":[38],"essence,":[39],"these":[40],"models":[41],"cannot":[42],"reason":[43],"in":[44,53,66,166],"an":[45,87],"open-ended":[46],"fashion,":[47],"answering":[49],"\u201cList":[50],"objects":[52],"scene.\u201d":[55],"We":[56,80,128,155],"introduce":[57],"first":[59,111],"method":[60,158],"address":[62],"setting":[68],"that":[69,146],"is":[70],"void":[71],"any":[73],"vocabulary":[74],"prior,":[75],"namely":[76],"vocabularyfree":[78],"setting.":[79],"leverage":[81],"large":[83],"vision-language":[84],"assistant":[85],"and":[86,97,143,161,169],"open-vocabulary":[88,170],"<tex":[89],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[90],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2":[91],"D$</tex>":[92],"segmenter":[94],"discover":[96],"ground":[98],"semantic":[99,144],"categories":[100],"on":[101],"posed":[103],"images.":[104],"To":[105],"form":[106],"masks,":[109],"we":[110],"partition":[112],"input":[114],"point":[115],"cloud":[116],"into":[117,124],"dense":[118],"superpoints,":[119],"which":[120],"then":[122],"merged":[123],"masks.":[127,154],"propose":[129],"novel":[131],"superpoint":[132],"merging":[133],"strategy":[134],"via":[135],"spectral":[136],"clustering,":[137],"accounting":[138],"for":[139],"both":[140,167],"mask":[141],"coherence":[142,145],"estimated":[148],"from":[149],"2D":[151],"object":[152],"evaluate":[156],"our":[157],"using":[159],"ScanNet200":[160],"Replica,":[162],"outperforming":[163],"existing":[164],"vocabulary-free":[168],"settings.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}