{"id":"https://openalex.org/W4415879096","doi":"https://doi.org/10.1109/iccv51701.2025.02613","title":"FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers","display_name":"FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415879096","doi":"https://doi.org/10.1109/iccv51701.2025.02613"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.02613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02613","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.15385","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050908073","display_name":"Haisheng Su","orcid":"https://orcid.org/0000-0002-4228-7439"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haisheng Su","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343082","display_name":"Junjie Zhang","orcid":"https://orcid.org/0000-0003-3425-2794"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Zhang","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005913248","display_name":"Fei Song","orcid":"https://orcid.org/0000-0003-1289-5502"},"institutions":[{"id":"https://openalex.org/I4392738153","display_name":"Luto Research (United Kingdom)","ror":"https://ror.org/04d2k2606","country_code":null,"type":"company","lineage":["https://openalex.org/I4392738153"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Feixiang Song","raw_affiliation_strings":["SenseAuto Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseAuto Research","institution_ids":["https://openalex.org/I4392738153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113827261","display_name":"Sanping Zhou","orcid":"https://orcid.org/0000-0003-4100-2304"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanping Zhou","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015297129","display_name":"Wei Wu","orcid":"https://orcid.org/0000-0002-8734-1582"},"institutions":[{"id":"https://openalex.org/I4392738153","display_name":"Luto Research (United Kingdom)","ror":"https://ror.org/04d2k2606","country_code":null,"type":"company","lineage":["https://openalex.org/I4392738153"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["SenseAuto Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseAuto Research","institution_ids":["https://openalex.org/I4392738153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087158377","display_name":"Junchi Yan","orcid":"https://orcid.org/0000-0001-9639-7679"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junchi Yan","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"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":"28145","last_page":"28155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.48019999265670776,"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":0.48019999265670776,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.17980000376701355,"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":0.08739999681711197,"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/encoder","display_name":"Encoder","score":0.5476999878883362},{"id":"https://openalex.org/keywords/depth-map","display_name":"Depth map","score":0.4970000088214874},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.47119998931884766},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4406999945640564},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.41589999198913574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41339999437332153},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.35850000381469727},{"id":"https://openalex.org/keywords/edge-detection","display_name":"Edge detection","score":0.3531999886035919},{"id":"https://openalex.org/keywords/measured-depth","display_name":"Measured depth","score":0.336899995803833},{"id":"https://openalex.org/keywords/depth-perception","display_name":"Depth perception","score":0.33230000734329224}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7186999917030334},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6358000040054321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6327999830245972},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.4970000088214874},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4406999945640564},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.35850000381469727},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.3531999886035919},{"id":"https://openalex.org/C113346285","wikidata":"https://www.wikidata.org/wiki/Q6804193","display_name":"Measured depth","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.33230000734329224},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C84824328","wikidata":"https://www.wikidata.org/wiki/Q4633097","display_name":"2D to 3D conversion","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C23746413","wikidata":"https://www.wikidata.org/wiki/Q1141379","display_name":"Seam carving","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C151416825","wikidata":"https://www.wikidata.org/wiki/Q934791","display_name":"Quadtree","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02613","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:2510.15385","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.15385","pdf_url":"https://arxiv.org/pdf/2510.15385","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.2510.15385","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.15385","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.15385","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.15385","pdf_url":"https://arxiv.org/pdf/2510.15385","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/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Detecting":[0],"3D":[1,119,185,191],"objects":[2],"accurately":[3],"from":[4,40,150,207],"multi-view":[5],"2D":[6,112,181],"images":[7],"is":[8,52,201],"a":[9,139],"challenging":[10],"yet":[11],"essential":[12],"task":[13],"in":[14,97],"the":[15,29,44,48,72,79,132,155,162,174,180,190,217,221],"field":[16],"of":[17,59,64,75,81,225],"autonomous":[18],"driving.":[19],"Current":[20],"methods":[21],"resort":[22],"to":[23,27,110,188],"integrating":[24],"depth":[25,50,57,86,164,199,205],"prediction":[26],"recover":[28],"spatial":[30,116],"information":[31,117],"for":[32,85,118,194,203],"object":[33,60],"query":[34,195],"decoding,":[35],"which":[36,67,123],"necessitates":[37],"explicit":[38],"supervision":[39,74,200],"LiDAR":[41],"points":[42,77],"during":[43],"training":[45],"phase.":[46],"However,":[47],"predicted":[49],"quality":[51],"still":[53],"unsatisfactory":[54],"such":[55],"as":[56],"discontinuity":[58],"boundaries":[61],"and":[62,78,91,147,168,184,210,223],"indistinction":[63],"small":[65],"objects,":[66],"are":[68,94],"mainly":[69],"caused":[70],"by":[71,142],"sparse":[73],"projected":[76],"use":[80],"high-level":[82],"image":[83,113,182],"features":[84,114,183,193],"prediction.":[87],"Besides,":[88],"cross-view":[89,167],"consistency":[90],"scale":[92],"invariance":[93],"also":[95],"overlooked":[96],"previous":[98],"methods.":[99],"In":[100],"this":[101],"paper,":[102],"we":[103],"introduce":[104],"Frequency-aware":[105,133],"Positional":[106,175],"Depth":[107,158,176],"Embedding":[108],"(FreqPDE)":[109],"equip":[111],"with":[115,166],"detection":[120],"transformer":[121],"decoder,":[122],"can":[124],"be":[125],"obtained":[126],"through":[127],"three":[128],"main":[129],"modules.":[130],"Specifically,":[131],"Spatial":[134],"Pyramid":[135],"Encoder":[136,177],"(FSPE)":[137],"constructs":[138],"feature":[140],"pyramid":[141],"combining":[143],"high-frequency":[144],"edge":[145],"clues":[146],"low-frequency":[148],"semantics":[149],"different":[151],"levels":[152],"respectively.":[153],"Then":[154],"Cross-view":[156],"Scale-invariant":[157],"Predictor":[159],"(CSDP)":[160],"estimates":[161],"pixel-level":[163],"distribution":[165,211],"efficient":[169],"channel":[170],"attention":[171],"mechanism.":[172],"Finally,":[173],"(PDE)":[178],"combines":[179],"position":[186],"embeddings":[187],"generate":[189],"depth-aware":[192],"decoding.":[196],"Additionally,":[197],"hybrid":[198],"adopted":[202],"complementary":[204],"learning":[206],"both":[208],"metric":[209],"aspects.":[212],"Extensive":[213],"experiments":[214],"conducted":[215],"on":[216],"nuScenes":[218],"dataset":[219],"demonstrate":[220],"effectiveness":[222],"superiority":[224],"our":[226],"proposed":[227],"method.":[228]},"counts_by_year":[],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-21T00:00:00"}