{"id":"https://openalex.org/W4416750358","doi":"https://doi.org/10.1109/iros60139.2025.11245934","title":"SAFormer: Spatially Adaptive Transformer for Efficient and Multi-Resolution Occupancy Prediction","display_name":"SAFormer: Spatially Adaptive Transformer for Efficient and Multi-Resolution Occupancy Prediction","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750358","doi":"https://doi.org/10.1109/iros60139.2025.11245934"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035419332","display_name":"Song Tang","orcid":"https://orcid.org/0000-0003-2635-1872"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Song Tang","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou),Data Science and Analytics Thrust,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou),Data Science and Analytics Thrust,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101427138","display_name":"Qiang Wang","orcid":"https://orcid.org/0009-0009-3117-9078"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["HIT(Shenzhen),Department of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HIT(Shenzhen),Department of Computer Science and Technology,China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100730785","display_name":"Xiaowen Chu","orcid":"https://orcid.org/0000-0001-9745-4372"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaowen Chu","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou),Data Science and Analytics Thrust,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou),Data Science and Analytics Thrust,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":"4150","last_page":"4157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5092999935150146,"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":0.5092999935150146,"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":0.08179999887943268,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.04989999905228615,"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/inference","display_name":"Inference","score":0.5965999960899353},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49309998750686646},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48899999260902405},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3675000071525574},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3634999990463257},{"id":"https://openalex.org/keywords/occupancy","display_name":"Occupancy","score":0.3612000048160553},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3598000109195709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819100022315979},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5965999960899353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5095999836921692},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39500001072883606},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C160331591","wikidata":"https://www.wikidata.org/wiki/Q7075743","display_name":"Occupancy","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3598000109195709},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3208000063896179},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.299699991941452},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2565639579","https://openalex.org/W3035574168","https://openalex.org/W3109395584","https://openalex.org/W3109428934","https://openalex.org/W3215584334","https://openalex.org/W4312894406","https://openalex.org/W4382450829","https://openalex.org/W4382464460","https://openalex.org/W4386066358","https://openalex.org/W4386083035","https://openalex.org/W4390873564","https://openalex.org/W4390874310","https://openalex.org/W4390874817","https://openalex.org/W4401414288","https://openalex.org/W4402713134","https://openalex.org/W4402754282","https://openalex.org/W4402772482","https://openalex.org/W4404005296","https://openalex.org/W4405785635","https://openalex.org/W4415796982"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"and":[1,28,61,137,159],"efficient":[2,42,82],"3D":[3,76],"scene":[4,91,157],"understanding":[5],"from":[6],"multi-view":[7],"images":[8],"remains":[9],"a":[10,37,95],"fundamental":[11],"challenge":[12],"in":[13,155,170],"autonomous":[14,171],"driving.":[15,172],"Existing":[16],"methods":[17],"often":[18],"struggle":[19],"with":[20],"high-dimensional":[21],"features,":[22],"leading":[23],"to":[24,52,73,135,141],"excessive":[25],"computational":[26,102],"costs":[27],"memory":[29,138],"usage.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"present":[35],"SAFormer,":[36],"novel":[38],"transformer-based":[39],"framework":[40],"for":[41,167],"spatially":[43],"adaptive":[44],"occupancy":[45],"prediction.":[46],"SAFormer":[47],"incorporates":[48],"two":[49],"key":[50],"techniques":[51],"reduce":[53],"resource":[54],"consumption:":[55],"Octree-based":[56,70],"Multi-resolution":[57],"Feature":[58],"(OMRF)":[59],"Learning":[60],"Spatial-Adaptive":[62],"Progressive":[63],"Query":[64],"(SAPQ).":[65],"First,":[66],"OMRF":[67],"introduces":[68],"an":[69],"hierarchical":[71],"structure":[72],"compress":[74],"multi-resolution":[75],"feature":[77],"volumes.":[78],"Second,":[79],"SAPQ":[80],"facilitates":[81],"information":[83],"flow":[84],"across":[85],"different":[86],"scales":[87],"while":[88,110,129],"effectively":[89],"addressing":[90],"sparsity.":[92],"It":[93],"employs":[94],"region-aware":[96],"query":[97],"mechanism":[98],"that":[99,123],"intelligently":[100],"allocates":[101],"resources,":[103],"processing":[104],"safety-critical":[105,162],"regions":[106],"at":[107,114],"high":[108],"resolution":[109],"handling":[111],"background":[112],"elements":[113],"lower":[115],"resolutions.":[116],"Experiments":[117],"on":[118,145],"the":[119],"nuScenes":[120],"dataset":[121],"demonstrate":[122],"our":[124,149],"method":[125],"achieves":[126],"state-of-the-art":[127],"performance":[128],"significantly":[130],"reducing":[131],"inference":[132],"latency":[133],"(up":[134,140],"3\u00d7)":[136],"cost":[139],"2.9\u00d7).":[142],"Additional":[143],"experiments":[144],"SSCBench-KITTI-360":[146],"further":[147],"validate":[148],"approach\u2019s":[150],"generalizability.":[151],"Our":[152],"approach":[153],"excels":[154],"managing":[156],"sparsity":[158],"recognizing":[160],"small,":[161],"objects,":[163],"highlighting":[164],"its":[165],"potential":[166],"practical":[168],"applications":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}