{"id":"https://openalex.org/W7163989174","doi":"https://doi.org/10.48550/arxiv.2606.08014","title":"GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence","display_name":"GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence","publication_year":2026,"publication_date":"2026-06-06","ids":{"openalex":"https://openalex.org/W7163989174","doi":"https://doi.org/10.48550/arxiv.2606.08014"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08014","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08014","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.08014","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138204020","display_name":"Liang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053131871","display_name":"Fangjing Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Fangjing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138206203","display_name":"Jinyu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138281803","display_name":"Feng Zheng","orcid":"https://orcid.org/0009-0008-5227-6267"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9222999811172485,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9222999811172485,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.02280000038444996,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.006099999882280827,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.7739999890327454},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6269999742507935},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5501000285148621},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5333999991416931},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4343999922275543},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42160001397132874},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.37869998812675476},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3569999933242798}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7739999890327454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7299000024795532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7142000198364258},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6269999742507935},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5501000285148621},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5333999991416931},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47859999537467957},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4343999922275543},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.37869998812675476},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.30169999599456787},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08014","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08014","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.08014","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08014","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.6918623447418213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"3D":[1,23,91,105,119],"instance":[2,92,134,138],"segmentation":[3,52,93,178],"in":[4,47,55,175],"point":[5],"cloud":[6],"data":[7,76],"is":[8,66,70],"critical":[9],"for":[10],"machine":[11],"vision":[12],"applications.":[13],"Recent":[14],"advancements":[15],"leverage":[16],"multiple":[17],"pre-trained":[18],"foundation":[19],"models":[20],"to":[21,44,112],"generate":[22],"proposals,":[24],"followed":[25],"by":[26,72],"the":[27,59,102,114,133],"application":[28],"of":[29],"proposal":[30,120,147],"aggregation":[31],"methods,":[32],"which":[33,100],"significantly":[34],"enhance":[35],"performance.":[36],"However,":[37],"they":[38],"often":[39],"produce":[40],"sub-optimal":[41],"results":[42],"due":[43],"inherent":[45],"variations":[46],"confidence":[48,115],"levels":[49],"across":[50,154],"different":[51,155],"models,":[53],"resulting":[54],"a":[56,88,118,124],"bias":[57,65],"toward":[58],"model":[60],"with":[61],"higher":[62],"confidence.":[63],"This":[64],"inherently":[67],"model-dependent":[68],"and":[69,79,108,123,137],"influenced":[71],"factors":[73],"such":[74],"as":[75],"preprocessing":[77],"techniques":[78],"training":[80],"strategies.":[81],"To":[82],"address":[83],"this":[84,143],"bias,":[85],"we":[86],"propose":[87],"novel,":[89],"training-free":[90],"approach":[94],"via":[95],"Geometric":[96],"Visual":[97],"Correspondence":[98],"(GVC-Seg),":[99],"exploits":[101],"correspondence":[103],"between":[104],"geometric":[106],"cues":[107,111],"2D":[109],"visual":[110],"mitigate":[113],"bias.":[116],"Additionally,":[117],"generation":[121,136],"module":[122,129],"mask-aware":[125],"CLIP":[126],"feature":[127],"extraction":[128],"are":[130],"introduced":[131],"during":[132],"mask":[135],"semantic":[139,177],"reasoning,":[140],"respectively.":[141],"In":[142],"way,":[144],"GVC-Seg":[145],"enhances":[146],"quality":[148],"assessment,":[149],"ensuring":[150],"unbiased":[151],"ensemble":[152],"learning":[153],"models.":[156],"Extensive":[157],"experiments":[158],"demonstrate":[159],"that":[160],"our":[161],"method":[162],"achieves":[163],"state-of-the-art":[164],"performance":[165],"on":[166],"several":[167],"challenging":[168],"benchmarks,":[169],"while":[170],"also":[171],"exhibiting":[172],"strong":[173],"potential":[174],"open-vocabulary":[176],"settings.":[179]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-10T00:00:00"}