{"id":"https://openalex.org/W4416749909","doi":"https://doi.org/10.1109/iros60139.2025.11247407","title":"ET-Former: Efficient Triplane Deformable Attention for 3D Semantic Scene Completion From Monocular Camera","display_name":"ET-Former: Efficient Triplane Deformable Attention for 3D Semantic Scene Completion From Monocular Camera","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749909","doi":"https://doi.org/10.1109/iros60139.2025.11247407"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247407","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":"article","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/A5100676081","display_name":"Jing Liang","orcid":"https://orcid.org/0000-0003-0811-0223"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Liang","raw_affiliation_strings":["University of Maryland,College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075992669","display_name":"He Yin","orcid":"https://orcid.org/0000-0002-4924-3543"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He Yin","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030004778","display_name":"XueweiTony Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"XueweiTony Qi","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108885409","display_name":"Jong Jin Park","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jong Jin Park","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100964116","display_name":"Min Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Sun","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056472890","display_name":"Rajasimman Madhivanan","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajasimman Madhivanan","raw_affiliation_strings":["Amazon Lab126"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland,College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"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":0.32676796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2313","last_page":"2320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.3400999903678894,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.3400999903678894,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.30640000104904175,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.22579999268054962,"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/monocular","display_name":"Monocular","score":0.7494000196456909},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.5831000208854675},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45649999380111694},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.40950000286102295},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.38760000467300415},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.3555999994277954},{"id":"https://openalex.org/keywords/monocular-vision","display_name":"Monocular vision","score":0.3456000089645386},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.325300008058548}],"concepts":[{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7494000196456909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7276999950408936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228000164031982},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6251000165939331},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.40950000286102295},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.38760000467300415},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247407","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":38,"referenced_works":["https://openalex.org/W2132947399","https://openalex.org/W2152671441","https://openalex.org/W2194775991","https://openalex.org/W2557465155","https://openalex.org/W2565639579","https://openalex.org/W2963426391","https://openalex.org/W2963627347","https://openalex.org/W2990026901","https://openalex.org/W2991216808","https://openalex.org/W3034868495","https://openalex.org/W3034961469","https://openalex.org/W3108776058","https://openalex.org/W3109395584","https://openalex.org/W3126856052","https://openalex.org/W3138270694","https://openalex.org/W3173668541","https://openalex.org/W3174865552","https://openalex.org/W3175844808","https://openalex.org/W3195680177","https://openalex.org/W3203806429","https://openalex.org/W3215584334","https://openalex.org/W4230575152","https://openalex.org/W4312641958","https://openalex.org/W4312894406","https://openalex.org/W4312960790","https://openalex.org/W4382466543","https://openalex.org/W4383108371","https://openalex.org/W4386066358","https://openalex.org/W4386075718","https://openalex.org/W4386076275","https://openalex.org/W4386083035","https://openalex.org/W4389286635","https://openalex.org/W4390874310","https://openalex.org/W4401416274","https://openalex.org/W4402753672","https://openalex.org/W4403770187","https://openalex.org/W4404005296","https://openalex.org/W4415796982"],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"ET-Former,":[2],"a":[3,12,19,37,65,148,160],"novel":[4],"end-to-end":[5],"algorithm":[6],"for":[7,32],"semantic":[8,20,33,58,79],"scene":[9,49],"completion":[10],"using":[11],"single":[13,24],"monocular":[14],"camera.":[15],"Our":[16],"approach":[17,43],"generates":[18],"occupancy":[21],"map":[22],"from":[23,134,140],"RGB":[25],"observation":[26],"while":[27,116],"simultaneously":[28],"providing":[29],"uncertainty":[30,81],"estimates":[31],"predictions.":[34,59,76],"By":[35],"designing":[36],"triplane-based":[38],"deformable":[39],"attention":[40],"mechanism,":[41],"our":[42],"improves":[44,128],"geometric":[45],"understanding":[46],"of":[47,64,74,132,154],"the":[48,62,72,96,100,105,118,129],"than":[50],"other":[51],"SOTA":[52,130],"approaches":[53],"and":[54,80,91,111,138],"reduces":[55],"noise":[56],"in":[57,95],"Additionally,":[60],"through":[61],"use":[63],"Conditional":[66],"Variational":[67],"AutoEncoder":[68],"(CVAE),":[69],"we":[70],"estimate":[71],"uncertainties":[73],"these":[75],"The":[77],"generated":[78],"maps":[82],"will":[83],"help":[84],"formulate":[85],"navigation":[86],"strategies":[87],"that":[88],"facilitate":[89],"safe":[90],"permissible":[92],"decision":[93],"making":[94],"future.":[97],"Evaluated":[98],"on":[99,144],"Semantic-KITTI":[101],"dataset,":[102],"ET-Former":[103],"achieves":[104],"highest":[106],"Intersection":[107],"over":[108],"Union":[109],"(IoU)":[110],"mean":[112],"IoU":[113,133],"(mIoU)":[114],"scores":[115,131],"maintaining":[117],"lowest":[119],"GPU":[120],"memory":[121,152],"usage,":[122],"surpassing":[123],"state-of-the-art":[124],"(SOTA)":[125],"methods.":[126,166],"It":[127],"44.71":[135],"to":[136,142,164],"51.49":[137],"mIoU":[139],"15.04":[141],"16.30":[143],"SeamnticKITTI":[145],"test,":[146],"with":[147],"notably":[149],"low":[150],"training":[151],"consumption":[153],"10.9":[155],"GB,":[156],"achieving":[157],"at":[158],"least":[159],"25%":[161],"reduction":[162],"compared":[163],"previous":[165],"Project":[167],"page:":[168],"https://github.com/amazon-science/ET-Former.":[169]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}