{"id":"https://openalex.org/W7154090079","doi":"https://doi.org/10.48550/arxiv.2604.09232","title":"Neural Distribution Prior for LiDAR Out-of-Distribution Detection","display_name":"Neural Distribution Prior for LiDAR Out-of-Distribution Detection","publication_year":2026,"publication_date":"2026-04-10","ids":{"openalex":"https://openalex.org/W7154090079","doi":"https://doi.org/10.48550/arxiv.2604.09232"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.09232","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09232","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":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.2604.09232","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122851245","display_name":"Zizhao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zizhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113750451","display_name":"Zhengkang Xiang","orcid":"https://orcid.org/0009-0005-8322-8696"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang, Zhengkang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051951717","display_name":"Jiayang Ao","orcid":"https://orcid.org/0000-0001-6416-1215"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ao, Jiayang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133498805","display_name":"Feng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122854758","display_name":"Joseph West","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"West, Joseph","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133514745","display_name":"Kourosh Khoshelham","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khoshelham, Kourosh","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":0.6004999876022339,"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":0.6004999876022339,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.15389999747276306,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.052400000393390656,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/robustness","display_name":"Robustness (evolution)","score":0.7319999933242798},{"id":"https://openalex.org/keywords/lidar","display_name":"Lidar","score":0.5949000120162964},{"id":"https://openalex.org/keywords/visibility","display_name":"Visibility","score":0.5120999813079834},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43869999051094055},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.387800008058548},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3619000017642975},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3580999970436096},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.3564000129699707}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7319999933242798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666100025177002},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.5949000120162964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5618000030517578},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.5120999813079834},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4530999958515167},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3619000017642975},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3564000129699707},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3522000014781952},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C149717495","wikidata":"https://www.wikidata.org/wiki/Q117806","display_name":"Gamma distribution","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.09232","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09232","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":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.2604.09232","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09232","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":null,"license_id":null,"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":{"LiDAR-based":[0],"perception":[1],"is":[2,169,181],"critical":[3],"for":[4,193],"autonomous":[5],"driving":[6],"due":[7],"to":[8,11,28],"its":[9],"robustness":[10],"poor":[12],"lighting":[13],"and":[14,25,57,84,107,146],"visibility":[15],"conditions.":[16],"Yet,":[17],"current":[18],"models":[19,77],"operate":[20],"under":[21],"the":[22,35,48,69,78,100,144,164,175],"closed-set":[23],"assumption":[24],"often":[26],"fail":[27],"recognize":[29],"unexpected":[30],"out-of-distribution":[31],"(OOD)":[32],"objects":[33],"in":[34,53],"open":[36],"world.":[37],"Existing":[38],"OOD":[39,55,87,122,129,136,154,186],"scoring":[40,187],"functions":[41],"exhibit":[42],"limited":[43],"performance":[44],"because":[45],"they":[46],"ignore":[47],"pronounced":[49],"class":[50,61],"imbalance":[51],"inherent":[52],"LiDAR":[54,195],"detection":[56,155],"assume":[58],"a":[59,74,93,119,158],"uniform":[60],"distribution.":[62],"To":[63],"address":[64],"this":[65],"limitation,":[66],"we":[67],"propose":[68],"Neural":[70],"Distribution":[71],"Prior":[72],"(NDP),":[73],"framework":[75,180],"that":[76,125,150],"distributional":[79],"structure":[80],"of":[81,104,161],"network":[82],"predictions":[83],"adaptively":[85],"reweights":[86],"scores":[88],"based":[89],"on":[90,143,163],"alignment":[91],"with":[92,183],"learned":[94],"distribution":[95,102],"prior.":[96],"NDP":[97,151],"dynamically":[98],"captures":[99],"logit":[101],"patterns":[103],"training":[105,137],"data":[106],"corrects":[108],"class-dependent":[109],"confidence":[110],"bias":[111],"through":[112],"an":[113,190],"attention-based":[114],"module.":[115],"We":[116],"further":[117],"introduce":[118],"Perlin":[120],"noise-based":[121],"synthesis":[123],"strategy":[124],"generates":[126],"diverse":[127],"auxiliary":[128],"samples":[130],"from":[131],"input":[132],"scans,":[133],"enabling":[134],"robust":[135],"without":[138],"external":[139],"datasets.":[140],"Extensive":[141],"experiments":[142],"SemanticKITTI":[145],"STU":[147,165],"benchmarks":[148],"demonstrate":[149],"substantially":[152],"improves":[153],"performance,":[156],"achieving":[157],"point-level":[159],"AP":[160],"61.31%":[162],"test":[166],"set,":[167],"which":[168],"more":[170],"than":[171,174],"10$\\times$":[172],"higher":[173],"previous":[176],"best":[177],"result.":[178],"Our":[179],"compatible":[182],"various":[184],"existing":[185],"formulations,":[188],"providing":[189],"effective":[191],"solution":[192],"open-world":[194],"perception.":[196]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-14T00:00:00"}