{"id":"https://openalex.org/W4405095593","doi":"https://doi.org/10.1109/iccv51701.2025.02446","title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-Based Online Scene Understanding","display_name":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-Based Online Scene Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405095593","doi":"https://doi.org/10.1109/iccv51701.2025.02446"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.04380","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074232124","display_name":"Yuqi Wu","orcid":"https://orcid.org/0000-0002-6527-2221"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Wu","raw_affiliation_strings":["Tsinghua University,Department of Automation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006396086","display_name":"Wenzhao Zheng","orcid":"https://orcid.org/0000-0001-7188-3734"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhao Zheng","raw_affiliation_strings":["Tsinghua University,Department of Automation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102491687","display_name":"Sicheng Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sicheng Zuo","raw_affiliation_strings":["Tsinghua University,Department of Automation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102942331","display_name":"Yuanhui Huang","orcid":"https://orcid.org/0000-0002-4774-7449"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanhui Huang","raw_affiliation_strings":["Tsinghua University,Department of Automation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055646953","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0002-6002-291X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["Tsinghua University,Department of Automation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460385","display_name":"Jiwen Lu","orcid":"https://orcid.org/0000-0002-6121-5529"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiwen Lu","raw_affiliation_strings":["Tsinghua University,Department of Automation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00110575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26360","last_page":"26370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9957000017166138,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9957000017166138,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9954000115394592,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9939000010490417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/occupancy","display_name":"Occupancy","score":0.9228652715682983},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.8337637186050415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45995843410491943},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45297732949256897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42529332637786865},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.35640376806259155},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12385538220405579},{"id":"https://openalex.org/keywords/architectural-engineering","display_name":"Architectural engineering","score":0.08550906181335449}],"concepts":[{"id":"https://openalex.org/C160331591","wikidata":"https://www.wikidata.org/wiki/Q7075743","display_name":"Occupancy","level":2,"score":0.9228652715682983},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8337637186050415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45995843410491943},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45297732949256897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42529332637786865},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.35640376806259155},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12385538220405579},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.08550906181335449}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.04380","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.04380","pdf_url":"https://arxiv.org/pdf/2412.04380","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.04380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.04380","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":"pmh:oai:arXiv.org:2412.04380","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.04380","pdf_url":"https://arxiv.org/pdf/2412.04380","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2829952131","display_name":null,"funder_award_id":"62125603,62321005,62336004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5196092873","display_name":null,"funder_award_id":"L247009","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"3D":[0,18,58,83,130,135,155,196],"occupancy":[1,59,131,197,213],"prediction":[2,60,198,214],"provides":[3],"a":[4,30,69,206],"comprehensive":[5],"description":[6],"of":[7,152,165,193],"the":[8,45,78,93,106,118,128,133,162,191,194,211],"surrounding":[9],"scenes":[10,176],"and":[11,33,67,86,102,109,146,209,218],"has":[12],"become":[13],"an":[14,56,140,148,182],"essential":[15],"task":[16,61],"for":[17],"perception.":[19],"Most":[20],"existing":[21,203],"methods":[22,204],"focus":[23],"on":[24,186],"offline":[25],"perception":[26],"from":[27,105,132],"one":[28],"or":[29],"few":[31],"views":[32],"cannot":[34],"be":[35],"applied":[36],"to":[37,42,62,73,116,126,189],"embodied":[38,49,57,94,178,195,212],"agents":[39],"that":[40],"demand":[41],"gradually":[43,158],"perceive":[44],"scene":[46,80],"through":[47,161,177],"progressive":[48],"exploration.":[50,179],"In":[51],"this":[52,64],"paper,":[53],"we":[54,99,122],"formulate":[55],"target":[63],"practical":[65],"scenario":[66],"propose":[68],"Gaussian-based":[70],"EmbodiedOcc":[71,138,201],"framework":[72],"accomplish":[74],"it.":[75],"We":[76,180],"initialize":[77],"global":[79,129,150],"with":[81,154,171,215],"uniform":[82],"semantic":[84,101],"Gaussians":[85],"progressively":[87],"update":[88],"local":[89,163,187],"regions":[90],"observed":[91,107],"by":[92,205],"agent.":[95],"For":[96],"each":[97],"update,":[98],"extract":[100],"structural":[103],"features":[104],"image":[108],"efficiently":[110],"incorporate":[111],"them":[112],"via":[113],"deformable":[114],"cross-attention":[115],"refine":[117],"regional":[119,166],"Gaussians.":[120,136,156],"Finally,":[121],"employ":[123],"Gaussian-to-voxel":[124],"splatting":[125],"obtain":[127],"updated":[134],"Our":[137,200],"assumes":[139],"unknown":[141],"(i.e.,":[142],"uniformly":[143],"distributed)":[144],"environment":[145],"maintains":[147],"explicit":[149],"memory":[151],"it":[153],"It":[157],"gains":[159],"knowledge":[160],"refinement":[164],"Gaussians,":[167],"which":[168],"is":[169],"consistent":[170],"how":[172],"humans":[173],"understand":[174],"new":[175],"reorganize":[181],"EmbodiedOcc-ScanNet":[183],"benchmark":[184],"based":[185],"annotations":[188],"facilitate":[190],"evaluation":[192],"task.":[199],"outperforms":[202],"large":[207],"margin":[208],"accomplishes":[210],"high":[216],"accuracy":[217],"efficiency.":[219],"Code:":[220],"https://github.com/YkiWu/EmbodiedOcc.":[221]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}