{"id":"https://openalex.org/W4413925552","doi":"https://doi.org/10.1109/icra55743.2025.11128708","title":"Deep Height Decoupling for Precise Vision-Based 3D Occupancy Prediction","display_name":"Deep Height Decoupling for Precise Vision-Based 3D Occupancy Prediction","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925552","doi":"https://doi.org/10.1109/icra55743.2025.11128708"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5100663519","display_name":"Yuan Wu","orcid":"https://orcid.org/0000-0002-9750-9297"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Wu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology,PCA Lab, Key Lab of Intelligent Perception and Systems for HighDimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology,PCA Lab, Key Lab of Intelligent Perception and Systems for HighDimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101741027","display_name":"Zhiqiang Yan","orcid":"https://orcid.org/0000-0003-3502-438X"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Yan","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology,PCA Lab, Key Lab of Intelligent Perception and Systems for HighDimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology,PCA Lab, Key Lab of Intelligent Perception and Systems for HighDimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050214771","display_name":"Zhengxue Wang","orcid":"https://orcid.org/0000-0002-4668-2559"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengxue Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology,PCA Lab, Key Lab of Intelligent Perception and Systems for HighDimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology,PCA Lab, Key Lab of Intelligent Perception and Systems for HighDimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331094","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-9851-6376"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["College of Computer Science, Nankai University,Tianjin,China,300071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University,Tianjin,China,300071","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030769176","display_name":"Le Hui","orcid":"https://orcid.org/0000-0003-0851-6805"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Hui","raw_affiliation_strings":["Northwestern Polytechnical University,Electronics and Information,Xi'an,China,710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Electronics and Information,Xi'an,China,710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101941394","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0001-8858-4378"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology,PCA Lab, Key Lab of Intelligent Perception and Systems for HighDimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology,PCA Lab, Key Lab of Intelligent Perception and Systems for HighDimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security","institution_ids":["https://openalex.org/I200845125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8699,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87464582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"12647","last_page":"12654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9986000061035156,"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":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10638","display_name":"Optical measurement and interference techniques","score":0.9825999736785889,"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/decoupling","display_name":"Decoupling (probability)","score":0.6917344927787781},{"id":"https://openalex.org/keywords/occupancy","display_name":"Occupancy","score":0.6314862370491028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5875322222709656},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5459519624710083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5269029140472412},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14088571071624756},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.07095086574554443}],"concepts":[{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.6917344927787781},{"id":"https://openalex.org/C160331591","wikidata":"https://www.wikidata.org/wiki/Q7075743","display_name":"Occupancy","level":2,"score":0.6314862370491028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5875322222709656},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5459519624710083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5269029140472412},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14088571071624756},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.07095086574554443},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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":34,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2752782242","https://openalex.org/W2966926453","https://openalex.org/W3109395584","https://openalex.org/W3138516171","https://openalex.org/W3202602509","https://openalex.org/W3215584334","https://openalex.org/W4226339983","https://openalex.org/W4312793957","https://openalex.org/W4312894406","https://openalex.org/W4382450829","https://openalex.org/W4382464460","https://openalex.org/W4382466775","https://openalex.org/W4386066358","https://openalex.org/W4386071563","https://openalex.org/W4386076423","https://openalex.org/W4386083035","https://openalex.org/W4390872375","https://openalex.org/W4390873564","https://openalex.org/W4390874155","https://openalex.org/W4390874310","https://openalex.org/W4399829383","https://openalex.org/W4401414288","https://openalex.org/W4402754007","https://openalex.org/W4402754236","https://openalex.org/W4402754282","https://openalex.org/W4402779632","https://openalex.org/W4402952464","https://openalex.org/W4403771534","https://openalex.org/W4404005296","https://openalex.org/W4404690819","https://openalex.org/W4408280739","https://openalex.org/W4410643823","https://openalex.org/W4413157611"],"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":{"The":[0],"task":[1],"of":[2,42],"vision-based":[3],"3D":[4,10,50],"occupancy":[5,169],"prediction":[6],"aims":[7],"to":[8,70,92,120,157],"reconstruct":[9],"geometry":[11],"and":[12,39,164],"estimate":[13],"its":[14],"semantic":[15],"classes":[16],"from":[17],"2D":[18,46,133],"color":[19],"images,":[20],"where":[21,139],"the":[22,45,53,95,109,123,132,159,172],"2D-to-3D":[23],"view":[24],"transformation":[25],"is":[26,155,188],"an":[27],"indispensable":[28],"step.":[29],"Most":[30],"previous":[31],"methods":[32],"conduct":[33],"forward":[34],"projection,":[35],"such":[36],"as":[37],"BEVPooling":[38],"VoxelPooling,":[40],"both":[41],"which":[43],"map":[44,125],"image":[47,134],"features":[48,57,67,135,143],"into":[49,126,136],"grids.":[51],"However,":[52],"current":[54],"grid":[55,141],"representing":[56],"within":[58,144],"a":[59,84,149],"certain":[60],"height":[61,72,90,102,110,124,146],"range":[62],"usually":[63],"introduces":[64],"many":[65],"confusing":[66,96],"that":[68,87],"belong":[69],"other":[71],"ranges.":[73,147],"To":[74],"address":[75],"this":[76],"challenge,":[77],"we":[78],"present":[79],"Deep":[80],"Height":[81,117],"Decoupling":[82],"(DHD),":[83],"novel":[85],"framework":[86],"incorporates":[88],"explicit":[89,105],"prior":[91],"filter":[93],"out":[94],"features.":[97],"Specifically,":[98],"DHD":[99,113],"first":[100],"predicts":[101],"maps":[103],"via":[104],"supervision.":[106],"Based":[107],"on":[108],"distribution":[111],"statistics,":[112],"designs":[114],"Mask":[115],"Guided":[116],"Sampling":[118],"(MGHS)":[119],"adaptively":[121],"decouple":[122],"multiple":[127,137],"binary":[128],"masks.":[129],"MGHS":[130],"projects":[131],"subspaces,":[138],"each":[140],"contains":[142],"reasonable":[145],"Finally,":[148],"Synergistic":[150],"Feature":[151],"Aggregation":[152],"(SFA)":[153],"module":[154],"deployed":[156],"enhance":[158],"feature":[160],"representation":[161],"through":[162],"channel":[163],"spatial":[165],"affinities,":[166],"enabling":[167],"further":[168],"refinement.":[170],"On":[171],"popular":[173],"Occ3D-nuScenes":[174],"benchmark,":[175],"our":[176],"method":[177],"achieves":[178],"state-of-the-art":[179],"performance":[180],"even":[181],"with":[182],"minimal":[183],"input":[184],"frames.":[185],"Source":[186],"code":[187],"released":[189],"at":[190],"https://github.com/yanzq95/DHD.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}