{"id":"https://openalex.org/W4415221783","doi":"https://doi.org/10.1109/lra.2025.3621977","title":"FreeMask3D: Zero-Shot Point Cloud Instance Segmentation Without 3D Training","display_name":"FreeMask3D: Zero-Shot Point Cloud Instance Segmentation Without 3D Training","publication_year":2025,"publication_date":"2025-10-15","ids":{"openalex":"https://openalex.org/W4415221783","doi":"https://doi.org/10.1109/lra.2025.3621977"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3621977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3621977","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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":null,"display_name":"Mingquan Zhou","orcid":"https://orcid.org/0009-0004-6447-3912"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingquan Zhou","raw_affiliation_strings":["Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013908038","display_name":"Xiaodong Wu","orcid":"https://orcid.org/0000-0002-6329-8938"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Wu","raw_affiliation_strings":["Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745886","display_name":"Chen He","orcid":"https://orcid.org/0000-0003-0124-8860"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen He","raw_affiliation_strings":["Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614962","display_name":"Ruiping Wang","orcid":"https://orcid.org/0000-0003-1830-2595"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiping Wang","raw_affiliation_strings":["Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083420537","display_name":"Xilin Chen","orcid":"https://orcid.org/0000-0003-3024-4404"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilin Chen","raw_affiliation_strings":["Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39263097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"12","first_page":"12301","last_page":"12308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9800999760627747,"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":0.9800999760627747,"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"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9751999974250793,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9745000004768372,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.7656000256538391},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.7459999918937683},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6873000264167786},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5710999965667725},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.41659998893737793},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.39959999918937683},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3750999867916107},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.35269999504089355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782999873161316},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7656000256538391},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.7459999918937683},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6873000264167786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6500999927520752},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5710999965667725},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.39959999918937683},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.396699994802475},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.35269999504089355},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3370000123977661},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.3046000003814697},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3621977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3621977","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121367935","display_name":null,"funder_award_id":"62461160331","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4523261873","display_name":null,"funder_award_id":"U21B2025","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7264320626","display_name":null,"funder_award_id":"62495082","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2460657278","https://openalex.org/W2507296351","https://openalex.org/W2594519801","https://openalex.org/W2769312834","https://openalex.org/W2895065325","https://openalex.org/W2904332125","https://openalex.org/W2928059219","https://openalex.org/W2959771705","https://openalex.org/W2962759414","https://openalex.org/W2963182550","https://openalex.org/W2979750740","https://openalex.org/W3004300126","https://openalex.org/W3034430142","https://openalex.org/W3034949383","https://openalex.org/W3035429765","https://openalex.org/W3116959466","https://openalex.org/W3166573884","https://openalex.org/W3172351327","https://openalex.org/W4312274934","https://openalex.org/W4312649925","https://openalex.org/W4312818263","https://openalex.org/W4312912313","https://openalex.org/W4312935996","https://openalex.org/W4383109105","https://openalex.org/W4386065742","https://openalex.org/W4386066076","https://openalex.org/W4386071839","https://openalex.org/W4386075561","https://openalex.org/W4386076523","https://openalex.org/W4390190234","https://openalex.org/W4390874575","https://openalex.org/W4399410938","https://openalex.org/W4402704512","https://openalex.org/W4402733574","https://openalex.org/W4402961794","https://openalex.org/W4403906550"],"related_works":[],"abstract_inverted_index":{"Point":[0],"cloud":[1,54],"instance":[2,55,72,75,78,84,89,112,115,125],"segmentation":[3,56,85,90],"is":[4,39],"crucial":[5],"for":[6],"3D":[7,26,52,60,101,111,168],"scene":[8],"understanding":[9],"in":[10,29],"robotics.":[11],"However,":[12],"existing":[13],"methods":[14],"heavily":[15],"rely":[16],"on":[17,91,147,177],"learning-based":[18],"approaches":[19],"that":[20,50,155],"require":[21],"large":[22,133],"amounts":[23],"of":[24,68,123,131],"annotated":[25],"data,":[27],"resulting":[28],"high":[30],"annotation":[31,61],"costs.":[32],"Therefore,":[33],"developing":[34],"cost-effective":[35],"and":[36,74,103,144,153],"data-efficient":[37],"solutions":[38],"essential.":[40],"To":[41],"this":[42],"end,":[43],"we":[44,80],"propose":[45],"FreeMask3D,":[46],"a":[47],"novel":[48],"approach":[49],"achieves":[51,157],"point":[53],"without":[57,167],"requiring":[58],"any":[59],"or":[62,159,180],"additional":[63],"training.":[64],"Our":[65],"method":[66],"consists":[67],"two":[69],"main":[70],"steps:":[71],"localization":[73],"recognition.":[76,142],"For":[77,114],"localization,":[79],"leverage":[81],"pre-trained":[82],"2D":[83],"models":[86],"to":[87,100,107,138,163],"perform":[88],"corresponding":[92],"RGB-D":[93],"images.":[94],"These":[95],"results":[96,171],"are":[97],"then":[98],"mapped":[99],"space":[102],"fused":[104],"across":[105],"frames":[106],"generate":[108],"the":[109,117,121,128],"final":[110],"masks.":[113],"recognition,":[116],"OpenSem":[118],"module":[119],"infers":[120],"category":[122],"each":[124],"by":[126],"leveraging":[127],"generalization":[129],"capabilities":[130,175],"cross-modal":[132],"models,":[134],"such":[135],"as":[136],"CLIP,":[137],"enable":[139],"open-vocabulary":[140,174],"semantic":[141],"Experiments":[143],"ablation":[145],"studies":[146],"four":[148],"challenging":[149],"benchmarks-ScanNetv2,":[150],"ScanNet200,":[151],"S3DIS,":[152],"Replica-demonstrate":[154],"FreeMask3D":[156],"competitive":[158],"superior":[160],"performance":[161],"compared":[162],"state-of-the-art":[164],"methods,":[165],"despite":[166],"supervision.":[169],"Qualitative":[170],"highlight":[172],"its":[173],"based":[176],"color,":[178],"affordance,":[179],"uncommon":[181],"phrase":[182],"description.":[183]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-16T00:00:00"}