{"id":"https://openalex.org/W7138252903","doi":"https://doi.org/10.48550/arxiv.2603.14076","title":"SGR-OCC: Evolving Monocular Priors for Embodied 3D Occupancy Prediction via Soft-Gating Lifting and Semantic-Adaptive Geometric Refinement","display_name":"SGR-OCC: Evolving Monocular Priors for Embodied 3D Occupancy Prediction via Soft-Gating Lifting and Semantic-Adaptive Geometric Refinement","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138252903","doi":"https://doi.org/10.48550/arxiv.2603.14076"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.14076","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14076","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.14076","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129650728","display_name":"Yiran Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069272393","display_name":"Simone Mentasti","orcid":"https://orcid.org/0000-0001-7059-413X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mentasti, Simone","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730706","display_name":"Xiaofeng Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Xiaofeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008765839","display_name":"Matteo Frosi","orcid":"https://orcid.org/0000-0002-5936-7945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frosi, Matteo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129714081","display_name":"Matteo Matteucci","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matteucci, Matteo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.6567999720573425,"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":0.6567999720573425,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.13660000264644623,"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":0.04650000110268593,"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/prior-probability","display_name":"Prior probability","score":0.7285000085830688},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6894999742507935},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.47920000553131104},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4749000072479248},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44519999623298645},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.40790000557899475},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4009999930858612},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.399399995803833},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7285000085830688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013999819755554},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6894999742507935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6672999858856201},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5759000182151794},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.35920000076293945},{"id":"https://openalex.org/C32653426","wikidata":"https://www.wikidata.org/wiki/Q3813641","display_name":"Background subtraction","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.3237000107765198},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C111151474","wikidata":"https://www.wikidata.org/wiki/Q1653368","display_name":"iCub","level":4,"score":0.30390000343322754},{"id":"https://openalex.org/C107551265","wikidata":"https://www.wikidata.org/wiki/Q1458245","display_name":"Displacement (psychology)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.14076","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14076","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.14076","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14076","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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,121],"semantic":[1,197],"occupancy":[2],"prediction":[3,186,215],"is":[4],"a":[5,75,94,104,113,147,190,196],"cornerstone":[6],"for":[7],"embodied":[8,214],"AI,":[9],"enabling":[10],"agents":[11],"to":[12,107,135],"perceive":[13],"dense":[14],"scene":[15],"geometry":[16],"and":[17,47,72,84,162,175,195,209,222,237],"semantics":[18],"incrementally":[19],"from":[20,166],"monocular":[21,37,89],"video":[22],"streams.":[23],"However,":[24],"current":[25],"online":[26],"frameworks":[27],"face":[28],"two":[29],"critical":[30],"bottlenecks:":[31],"the":[32,48,80,158,173,202],"inherent":[33],"depth":[34,101,127],"ambiguity":[35],"of":[36,82,193,199],"estimation":[38],"that":[39,98,179],"causes":[40],"\"feature":[41],"bleeding\"":[42],"at":[43],"object":[44],"boundaries":[45],",":[46],"\"cold":[49],"start\"":[50],"instability":[51],"where":[52],"uninitialized":[53],"temporal":[54,143],"fusion":[55],"layers":[56],"distort":[57],"high-quality":[58],"spatial":[59,90,164],"priors":[60,165],"during":[61],"early":[62,168],"training":[63],"stages.":[64],"In":[65,184,212],"this":[66],"paper,":[67],"we":[68,92,145],"propose":[69],"SGR-OCC":[70,180,188],"(Soft-Gating":[71],"Ray-refinement":[73],"Occupancy),":[74],"unified":[76],"framework":[77],"driven":[78],"by":[79,207],"philosophy":[81],"\"Inheritance":[83],"Evolution\".":[85],"To":[86,138],"perfectly":[87],"inherit":[88],"expertise,":[91],"introduce":[93],"Soft-Gating":[95],"Feature":[96],"Lifter":[97],"explicitly":[99],"models":[100],"uncertainty":[102],"via":[103],"Gaussian":[105],"gate":[106],"probabilistically":[108],"suppress":[109],"background":[110],"noise.":[111],"Furthermore,":[112],"Dynamic":[114],"Ray-Constrained":[115],"Anchor":[116],"Refinement":[117],"module":[118],"simplifies":[119],"complex":[120,241],"displacement":[122],"searches":[123],"into":[124],"efficient":[125],"1D":[126],"corrections":[128],"along":[129],"camera":[130],"rays,":[131],"ensuring":[132],"sub-voxel":[133],"adherence":[134],"physical":[136],"surfaces.":[137],"ensure":[139],"stable":[140],"evolution":[141],"toward":[142],"consistency,":[144],"employ":[146],"Two-Phase":[148],"Progressive":[149],"Training":[150],"Strategy":[151],"equipped":[152],"with":[153],"identity-initialized":[154],"fusion,":[155],"effectively":[156],"resolving":[157],"cold":[159],"start":[160],"problem":[161],"shielding":[163],"noisy":[167],"gradients.":[169],"Extensive":[170],"experiments":[171],"on":[172],"EmbodiedOcc-ScanNet":[174],"Occ-ScanNet":[176],"benchmarks":[177],"demonstrate":[178],"achieves":[181,189],"state-of-the-art":[182],"performance.":[183],"local":[185],"tasks,":[187,216],"completion":[191],"IoU":[192],"58.55$\\%$":[194],"mIoU":[198],"49.89$\\%$,":[200],"surpassing":[201],"previous":[203],"best":[204],"method,":[205],"EmbodiedOcc++,":[206],"3.65$\\%$":[208],"3.69$\\%$":[210],"respectively.":[211],"challenging":[213],"our":[217,229],"model":[218],"reaches":[219],"55.72$\\%$":[220],"SC-IoU":[221],"46.22$\\%$":[223],"mIoU.":[224],"Qualitative":[225],"results":[226],"further":[227],"confirm":[228],"model's":[230],"superior":[231],"capability":[232],"in":[233,240],"preserving":[234],"structural":[235],"integrity":[236],"boundary":[238],"sharpness":[239],"indoor":[242],"environments.":[243]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}