{"id":"https://openalex.org/W7216128482","doi":"https://doi.org/10.48550/arxiv.2610.01644","title":"SonarVoxNet: Diver Detection in 3D Bounding Box using 3D Sonar","display_name":"SonarVoxNet: Diver Detection in 3D Bounding Box using 3D Sonar","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7216128482","doi":"https://doi.org/10.48550/arxiv.2610.01644"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.01644","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01644","pdf_url":"https://arxiv.org/pdf/2610.01644","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.01644","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135836073","display_name":"Eugene Park","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Eugene","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155831757","display_name":"Jiwon Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Jiwon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147052111","display_name":"Seyoung Kan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kan, Seyoung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120536717","display_name":"Trung Dong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Trung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155403534","display_name":"Xiaomin Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Xiaomin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138733917","display_name":"Jane Shin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shin, Jane","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":true,"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/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.8593999743461609,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"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/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.8593999743461609,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T10036","display_name":"Advanced Neural Network Applications","score":0.05790000036358833,"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/T11698","display_name":"Underwater Acoustics Research","score":0.05490000173449516,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"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/diver-detection","display_name":"diver detection","score":0.9679999947547913},{"id":"https://openalex.org/keywords/autonomous-underwater-vehicles","display_name":"autonomous underwater vehicles","score":0.8730000257492065},{"id":"https://openalex.org/keywords/oriented-bounding-boxes","display_name":"oriented bounding boxes","score":0.5920000076293945},{"id":"https://openalex.org/keywords/cave-diving","display_name":"cave diving","score":0.7440000176429749},{"id":"https://openalex.org/keywords/underwater-perception","display_name":"underwater perception","score":0.3370000123977661}],"concepts":[{"id":"https://openalex.org/C555745239","wikidata":"https://www.wikidata.org/wiki/Q133220","display_name":"Sonar","level":2,"score":0.9093000292778015},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.7195000052452087},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7117000222206116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6014999747276306},{"id":"https://openalex.org/C181255713","wikidata":"https://www.wikidata.org/wiki/Q7662740","display_name":"Synthetic aperture sonar","level":3,"score":0.5867999792098999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5414000153541565},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C37054046","wikidata":"https://www.wikidata.org/wiki/Q641888","display_name":"Elevation (ballistics)","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.36059999465942383},{"id":"https://openalex.org/C145424490","wikidata":"https://www.wikidata.org/wiki/Q618465","display_name":"Remotely operated underwater vehicle","level":4,"score":0.3578999936580658},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C146160929","wikidata":"https://www.wikidata.org/wiki/Q751290","display_name":"Euler angles","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C157498722","wikidata":"https://www.wikidata.org/wiki/Q34929","display_name":"Three-dimensional space","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C89805583","wikidata":"https://www.wikidata.org/wiki/Q192940","display_name":"Accelerometer","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2700999975204468},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25619998574256897},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C108439606","wikidata":"https://www.wikidata.org/wiki/Q3305038","display_name":"Angular displacement","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.01644","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01644","pdf_url":"https://arxiv.org/pdf/2610.01644","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.01644","doi":"https://doi.org/10.48550/arxiv.2610.01644","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.01644","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.01644","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01644","pdf_url":"https://arxiv.org/pdf/2610.01644","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7216128482.pdf","grobid_xml":"https://content.openalex.org/works/W7216128482.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4416245942","https://openalex.org/W4417076074","https://openalex.org/W7134251354","https://openalex.org/W7204921770"],"related_works":["https://openalex.org/W7130515214","https://openalex.org/W2619654368","https://openalex.org/W7044059525","https://openalex.org/W1566361887","https://openalex.org/W7103653394","https://openalex.org/W2979836734","https://openalex.org/W1495383426","https://openalex.org/W2952053925","https://openalex.org/W4389777102","https://openalex.org/W7213958764"],"abstract_inverted_index":{"Autonomous":[0],"underwater":[1],"vehicles":[2],"(AUVs)":[3],"assisting":[4],"human":[5],"divers":[6,166],"must":[7],"continuously":[8],"track":[9],"not":[10],"only":[11,76],"the":[12,37,78,120,142,154,181,189,199,231],"diver's":[13],"3D":[14,50,116,144,157,162,194,227],"position":[15],"but":[16,54],"also":[17],"their":[18],"full-body":[19,221],"orientation.":[20],"However,":[21],"vision-based":[22],"perception":[23],"is":[24,153,198,224],"unreliable":[25],"underwater,":[26],"and":[27,59,68,74,92,109,183,213,240],"forward-looking":[28],"sonar":[29,51,117,145,158,228],"--":[30,35,138],"despite":[31],"being":[32],"widely":[33],"used":[34],"discards":[36],"elevation":[38,53],"information":[39],"needed":[40],"for":[41,64,69,165,233],"orientation":[42,163,215,223],"estimation,":[43],"posing":[44],"a":[45,89,106,126,173],"fundamental":[46],"limitation.":[47],"Recently":[48],"commercialized":[49],"preserves":[52],"produces":[55],"sparse,":[56],"noisy":[57],"returns,":[58],"existing":[60],"detectors":[61],"are":[62],"built":[63],"dense":[65],"LiDAR":[66],"data":[67],"targets":[70],"that":[71,188,220],"remain":[72],"upright":[73],"rotate":[75],"about":[77],"yaw":[79],"axis":[80],"(e.g.,":[81],"vehicles,":[82],"pedestrians),":[83],"making":[84],"them":[85],"unable":[86],"to":[87,115,131,139,148,204],"represent":[88],"freely":[90],"pitching":[91],"rolling":[93],"diver.":[94],"To":[95],"address":[96],"this":[97],"gap,":[98],"we":[99,186],"present":[100],"two":[101],"contributions.":[102],"First,":[103],"SonarVoxNet":[104],"adapts":[105],"voxel-based":[107],"encoder":[108],"an":[110],"anchor-free":[111],"center-based":[112],"detection":[113,184,197,211],"head":[114],"data,":[118],"replacing":[119],"conventional":[121],"yaw-only":[122,202],"rotation":[123,129,203],"representation":[124],"with":[125,160],"continuous":[127],"6D":[128],"parameterization":[130],"predict":[132],"full":[133,161],"9-DoF":[134],"oriented":[135],"bounding":[136],"boxes":[137],"our":[140],"knowledge,":[141],"first":[143,155],"diver":[146,196,222,237],"detector":[147],"do":[149],"so.":[150],"Second,":[151],"Diver3D":[152],"public":[156],"dataset":[159],"labels":[164],"in":[167],"diverse,":[168],"non-upright":[169],"poses,":[170],"collected":[171],"at":[172],"natural":[174],"cave-diving":[175],"site.":[176],"Through":[177],"controlled":[178],"ablations":[179],"over":[180],"backbone":[182],"head,":[185],"show":[187],"dominant":[190],"factor":[191],"behind":[192],"accurate":[193],"sonar-based":[195],"transition":[200,208],"from":[201,226],"full-SO(3)":[205],"rotation.":[206],"This":[207],"substantially":[209],"improves":[210],"accuracy":[212],"reduces":[214],"error.":[216],"These":[217],"results":[218],"demonstrate":[219],"recoverable":[225],"alone,":[229],"laying":[230],"groundwork":[232],"future":[234],"work":[235],"on":[236],"pose":[238],"estimation":[239],"diver-robot":[241],"interaction.":[242]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}
