{"id":"https://openalex.org/W7162422592","doi":"https://doi.org/10.48550/arxiv.2605.24243","title":"GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer","display_name":"GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer","publication_year":2026,"publication_date":"2026-05-22","ids":{"openalex":"https://openalex.org/W7162422592","doi":"https://doi.org/10.48550/arxiv.2605.24243"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.24243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24243","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":"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.2605.24243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005850407","display_name":"Diogo Lavado","orcid":"https://orcid.org/0009-0005-5302-0659"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lavado, Diogo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039437349","display_name":"Alessandra Micheletti","orcid":"https://orcid.org/0000-0002-5369-5657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Micheletti, Alessandra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5009777388","display_name":"Cl\u00e1udia Soares","orcid":"https://orcid.org/0000-0003-3071-6627"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soares, Cl\u00e0udia","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":0.8996000289916992,"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":0.8996000289916992,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.016699999570846558,"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":0.012299999594688416,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7494000196456909},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5982999801635742},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.583299994468689},{"id":"https://openalex.org/keywords/geometric-modeling","display_name":"Geometric modeling","score":0.5430999994277954},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.508400022983551},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47929999232292175},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.42309999465942383},{"id":"https://openalex.org/keywords/geometric-shape","display_name":"Geometric shape","score":0.3847000002861023},{"id":"https://openalex.org/keywords/solid-modeling","display_name":"Solid modeling","score":0.3767000138759613}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7494000196456909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6761999726295471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6111000180244446},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5982999801635742},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.5430999994277954},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44200000166893005},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.42309999465942383},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3750999867916107},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C197352929","wikidata":"https://www.wikidata.org/wiki/Q1074074","display_name":"Inductive bias","level":4,"score":0.36980000138282776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C136520226","wikidata":"https://www.wikidata.org/wiki/Q302814","display_name":"Geometric data analysis","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C181095308","wikidata":"https://www.wikidata.org/wiki/Q1541599","display_name":"Geometric primitive","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C56435381","wikidata":"https://www.wikidata.org/wiki/Q1196371","display_name":"Geometric transformation","level":3,"score":0.32280001044273376},{"id":"https://openalex.org/C40319758","wikidata":"https://www.wikidata.org/wiki/Q5535477","display_name":"Geometric design","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C39947850","wikidata":"https://www.wikidata.org/wiki/Q729523","display_name":"Geometric distribution","level":3,"score":0.29179999232292175},{"id":"https://openalex.org/C29123130","wikidata":"https://www.wikidata.org/wiki/Q874709","display_name":"Computational geometry","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2655999958515167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.24243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24243","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":"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.2605.24243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24243","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":"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":{"In":[0],"3D":[1,24,73,112,150],"scene":[2,151],"understanding,":[3,152],"deep":[4],"learning":[5],"models":[6,10,44],"rely":[7],"on":[8,125],"large":[9,43],"and":[11,45,54,148],"extensive":[12],"training":[13,47],"to":[14,32,122,145],"capture":[15],"basic":[16],"geometric":[17,34,63,70,93,143],"structures":[18],"that":[19,67,98],"are":[20],"present":[21],"in":[22,50],"the":[23,138],"data.":[25],"However,":[26],"existing":[27,78],"methods":[28],"lack":[29],"explicit":[30],"mechanisms":[31],"incorporate":[33],"information,":[35],"such":[36],"as":[37],"learnable":[38,69],"primitive":[39],"shapes,":[40],"often":[41],"necessitating":[42],"more":[46],"data":[48],"which":[49],"turn":[51],"increases":[52],"cost":[53],"can":[55],"limit":[56],"generalization.":[57],"We":[58,106],"introduce":[59],"GIBLy,":[60],"a":[61,154],"lightweight":[62,155],"inductive":[64],"bias":[65],"layer":[66,157],"integrates":[68],"priors":[71],"into":[72],"segmentation":[74,100,114],"pipelines.":[75],"GIBLy":[76],"enhances":[77],"architectures":[79],"--":[80,86],"whether":[81],"MLP-based,":[82],"convolution-based,":[83],"or":[84],"transformer-based":[85],"by":[87],"providing":[88],"features":[89],"aligned":[90],"with":[91,102,127,153],"simple":[92],"shapes":[94],"(and":[95],"thus":[96],"human-interpretable)":[97],"improve":[99],"performance":[101,118],"minimal":[103],"computational":[104],"overhead.":[105],"validate":[107],"our":[108],"approach":[109],"across":[110],"multiple":[111],"semantic":[113],"benchmarks,":[115],"demonstrating":[116],"consistent":[117],"gains,":[119],"including":[120],"up":[121],"+11.5%":[123],"mIoU":[124],"TS40K":[126],"PTV3,":[128],"while":[129],"adding":[130],"only":[131],"58K":[132],"extra":[133],"parameters.":[134],"Our":[135],"results":[136],"highlight":[137],"benefit":[139],"of":[140],"explicitly":[141],"encoding":[142],"structure":[144],"support":[146],"accurate":[147],"efficient":[149],"add-on":[156]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-27T00:00:00"}