{"id":"https://openalex.org/W7140287300","doi":"https://doi.org/10.48550/arxiv.2603.22757","title":"Multimodal Industrial Anomaly Detection via Geometric Prior","display_name":"Multimodal Industrial Anomaly Detection via Geometric Prior","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7140287300","doi":"https://doi.org/10.48550/arxiv.2603.22757"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.22757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22757","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.22757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130616161","display_name":"Min Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Min","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130556826","display_name":"Jinghui He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Jinghui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130601169","display_name":"Gang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Gang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130575601","display_name":"Jiachen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiachen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130629811","display_name":"Jin Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Jin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130605165","display_name":"Delong Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Delong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5130616161"],"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9233999848365784,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9233999848365784,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.006300000008195639,"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"}},{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.00570000009611249,"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/anomaly-detection","display_name":"Anomaly detection","score":0.7069000005722046},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5759000182151794},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5151000022888184},{"id":"https://openalex.org/keywords/geometric-data-analysis","display_name":"Geometric data analysis","score":0.4726000130176544},{"id":"https://openalex.org/keywords/geometric-shape","display_name":"Geometric shape","score":0.46230000257492065},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4528000056743622},{"id":"https://openalex.org/keywords/geometric-modeling","display_name":"Geometric modeling","score":0.41690000891685486},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4104999899864197},{"id":"https://openalex.org/keywords/geometric-transformation","display_name":"Geometric transformation","score":0.4041999876499176}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7069000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6427000164985657},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5759000182151794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5522000193595886},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5151000022888184},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5078999996185303},{"id":"https://openalex.org/C136520226","wikidata":"https://www.wikidata.org/wiki/Q302814","display_name":"Geometric data analysis","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C56435381","wikidata":"https://www.wikidata.org/wiki/Q1196371","display_name":"Geometric transformation","level":3,"score":0.4041999876499176},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C32209215","wikidata":"https://www.wikidata.org/wiki/Q5535483","display_name":"Geometric flow","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C32990609","wikidata":"https://www.wikidata.org/wiki/Q306542","display_name":"Transformation geometry","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C154968394","wikidata":"https://www.wikidata.org/wiki/Q5535474","display_name":"Geometric analysis","level":5,"score":0.314300000667572},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28690001368522644},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26589998602867126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.22757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22757","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.22757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22757","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":"article"},"sustainable_development_goals":[{"score":0.5481171607971191,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"purpose":[1],"of":[2,40,94,114],"multimodal":[3,32,115,154],"industrial":[4,33,155],"anomaly":[5,34,133,156],"detection":[6,35,55,157,165],"is":[7],"to":[8,25,78,89,109,145],"detect":[9,26],"complex":[10],"geometric":[11,42,81,92,100,121,138,147],"shape":[12,50],"defects":[13],"such":[14],"as":[15,117,119],"subtle":[16],"surface":[17,45],"deformations":[18],"and":[19,48,98,132,171],"irregular":[20],"contours":[21],"that":[22,152],"are":[23],"difficult":[24],"in":[27,53,124,164],"2D-based":[28],"methods.":[29],"However,":[30],"current":[31],"lacks":[36],"the":[37,91,95,112,120,142,160],"effective":[38],"use":[39],"crucial":[41],"information":[43],"like":[44],"normal":[46,86],"vectors":[47],"3D":[49,125],"topology,":[51],"resulting":[52],"low":[54],"accuracy.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,71,103],"propose":[61,72,104,129],"a":[62,73,105],"novel":[63],"Geometric":[64],"Prior-based":[65],"Anomaly":[66],"Detection":[67],"network":[68],"(GPAD).":[69],"Firstly,":[70],"point":[74],"cloud":[75],"expert":[76],"model":[77,158],"perform":[79],"fine-grained":[80],"feature":[82],"extraction,":[83],"employing":[84],"differential":[85],"vector":[87],"computation":[88],"enhance":[90,141],"details":[93],"extracted":[96],"features":[97],"generate":[99],"prior.":[101],"Secondly,":[102],"two-stage":[106],"fusion":[107,131],"strategy":[108],"efficiently":[110],"leverage":[111],"complementarity":[113],"data":[116],"well":[118],"prior":[122],"inherent":[123],"points.":[126],"We":[127],"further":[128],"attention":[130],"regions":[134],"segmentation":[135],"based":[136],"on":[137,167],"prior,":[139],"which":[140],"model's":[143],"ability":[144],"perceive":[146],"defects.":[148],"Extensive":[149],"experiments":[150],"show":[151],"our":[153],"outperforms":[159],"State-of-the-art":[161],"(SOTA)":[162],"methods":[163],"accuracy":[166],"both":[168],"MVTec-3D":[169],"AD":[170],"Eyecandies":[172],"datasets.":[173]},"counts_by_year":[],"updated_date":"2026-03-26T06:10:45.909354","created_date":"2026-03-26T00:00:00"}