{"id":"https://openalex.org/W7165754289","doi":"https://doi.org/10.48550/arxiv.2606.24353","title":"Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints","display_name":"Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7165754289","doi":"https://doi.org/10.48550/arxiv.2606.24353"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.24353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24353","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":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.2606.24353","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139247742","display_name":"Hojun Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choi, Hojun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043643745","display_name":"Seulbin Hwang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hwang, Seulbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030455706","display_name":"Dae Jung Kim","orcid":"https://orcid.org/0000-0003-1025-2044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Dae Jung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079352117","display_name":"K. Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Kisung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079082222","display_name":"Hyunjung Shim","orcid":"https://orcid.org/0000-0001-6796-1058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shim, Hyunjung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139250807","display_name":"Jinhan Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Jinhan","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/T10036","display_name":"Advanced Neural Network Applications","score":0.5059000253677368,"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":0.5059000253677368,"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":0.1273999959230423,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.07050000131130219,"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/segmentation","display_name":"Segmentation","score":0.5900999903678894},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5116000175476074},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5113000273704529},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4862000048160553},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.47290000319480896},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4498000144958496},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4041000008583069},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3862000107765198},{"id":"https://openalex.org/keywords/geometric-primitive","display_name":"Geometric primitive","score":0.3424000144004822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394999861717224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7024000287055969},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5900999903678894},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5752999782562256},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5113000273704529},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4862000048160553},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4041000008583069},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C181095308","wikidata":"https://www.wikidata.org/wiki/Q1541599","display_name":"Geometric primitive","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C2776863239","wikidata":"https://www.wikidata.org/wiki/Q7936601","display_name":"Visual hull","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.24353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24353","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.24353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24353","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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Bird's-eye":[0],"view":[1],"(BEV)":[2],"perception":[3,57],"fuses":[4],"multi-camera":[5],"images":[6],"into":[7,81],"a":[8,89],"unified":[9],"top-down":[10],"representation":[11],"for":[12,117,129,138],"autonomous":[13],"driving.":[14],"Despite":[15],"recent":[16],"progress,":[17],"state-of-the-art":[18,147],"methods":[19,151],"remain":[20],"confined":[21],"to":[22,28,46,176],"closed-set":[23,150],"scenarios,":[24],"making":[25],"them":[26],"vulnerable":[27],"unpredictable":[29],"real-world":[30],"environments.":[31],"In":[32],"this":[33],"work,":[34],"we":[35,86],"introduce":[36],"open-vocabulary":[37],"BEV":[38,56,126],"segmentation":[39],"(OVBS),":[40],"which":[41],"leverages":[42],"vision-language":[43],"models":[44],"(VLMs)":[45],"recognize":[47],"categories":[48],"beyond":[49],"the":[50,68,74,142,190],"training":[51],"set":[52],"while":[53],"maintaining":[54],"precise":[55],"and":[58,133,170],"real-time":[59],"efficiency.":[60,140],"A":[61],"key":[62],"challenge":[63],"in":[64,67,73],"OVBS":[65,91],"lies":[66],"3D":[69,103,115,130,135],"geometric":[70,104,131,136],"inconsistency":[71],"inherent":[72],"ill-posed":[75],"lifting":[76],"of":[77,178,193],"2D":[78],"VLM":[79],"semantics":[80],"BEV.":[82],"To":[83],"address":[84],"this,":[85],"propose":[87],"OVBEVSeg,":[88],"geometry-aware":[90],"framework":[92],"that":[93],"enhances":[94],"efficient":[95],"Gaussian":[96],"splatting":[97],"(GS)-based":[98],"unprojection":[99],"by":[100,152],"leveraging":[101],"robust":[102],"constraints":[105,128],"across":[106],"three":[107],"progressive":[108],"stages:":[109],"(1)":[110],"2D-to-BEV":[111],"pseudo-labeling":[112],"via":[113],"reliable":[114],"projection":[116],"OV":[118],"generalization;":[119],"(2)":[120],"joint":[121],"2D-BEV":[122],"per-scene":[123],"optimization":[124],"with":[125,160,168,174,187],"structural":[127],"consistency;":[132],"(3)":[134],"distillation":[137],"online":[139],"On":[141],"nuScenes":[143],"dataset,":[144],"OVBEVSeg":[145],"achieves":[146,183],"performance,":[148],"outperforming":[149],"15.3":[153],"mIoU":[154],"on":[155],"unseen":[156],"categories.":[157],"Remarkably,":[158],"even":[159],"no":[161],"novel-class":[162],"ground-truth":[163,179],"labels,":[164],"it":[165,182],"remains":[166],"competitive":[167],"self-":[169],"semi-supervised":[171],"baselines":[172],"trained":[173],"up":[175],"40%":[177],"annotations.":[180],"Furthermore,":[181],"2.5x":[184],"faster":[185],"inference":[186],"only":[188],"0.22x":[189],"memory":[191],"consumption":[192],"projection-based":[194],"methods.":[195],"Project":[196],"page:":[197],"https://hchoi256.github.io/projects/ovbevseg/.":[198]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-25T00:00:00"}