{"id":"https://openalex.org/W4401416274","doi":"https://doi.org/10.1109/icra57147.2024.10611261","title":"MonoOcc: Digging into Monocular Semantic Occupancy Prediction","display_name":"MonoOcc: Digging into Monocular Semantic Occupancy Prediction","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416274","doi":"https://doi.org/10.1109/icra57147.2024.10611261"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5103047903","display_name":"Yupeng Zheng","orcid":"https://orcid.org/0000-0003-4450-7586"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Yupeng Zheng","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University,China","Institute of Automation, Chinese Academy of Sciences,The State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,The State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026630522","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0003-0945-145X"},"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":"Xiang Li","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339792","display_name":"Pengfei Li","orcid":"https://orcid.org/0009-0009-8114-6207"},"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":"Pengfei Li","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030295721","display_name":"Yuhang Zheng","orcid":"https://orcid.org/0000-0001-9628-1940"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Yuhang Zheng","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University,China","Institute of Automation, Chinese Academy of Sciences,The State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,The State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024635574","display_name":"Bu Jin","orcid":"https://orcid.org/0000-0001-7577-2177"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bu Jin","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,The State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,The State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070959015","display_name":"Chengliang Zhong","orcid":"https://orcid.org/0000-0002-6200-0749"},"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":"Chengliang Zhong","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072177890","display_name":"Xiaoxiao Long","orcid":"https://orcid.org/0000-0002-3386-8805"},"institutions":[{"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":"Xiaoxiao Long","raw_affiliation_strings":["the University of Hong Kong,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"the University of Hong Kong,Department of Computer Science","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025049450","display_name":"Hao Zhao","orcid":"https://orcid.org/0000-0001-7903-581X"},"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":"Hao Zhao","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101736381","display_name":"Qichao Zhang","orcid":"https://orcid.org/0000-0002-8278-7083"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qichao Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,The State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,The State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7806,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.97795479,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"18398","last_page":"18405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9977999925613403,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9977999925613403,"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/T10028","display_name":"Topic Modeling","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/digging","display_name":"Digging","score":0.9433770775794983},{"id":"https://openalex.org/keywords/occupancy","display_name":"Occupancy","score":0.8365022540092468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6946308612823486},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5819199085235596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5369837880134583},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40087807178497314},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12276908755302429},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08645427227020264},{"id":"https://openalex.org/keywords/architectural-engineering","display_name":"Architectural engineering","score":0.06106686592102051}],"concepts":[{"id":"https://openalex.org/C2779080342","wikidata":"https://www.wikidata.org/wiki/Q4232202","display_name":"Digging","level":2,"score":0.9433770775794983},{"id":"https://openalex.org/C160331591","wikidata":"https://www.wikidata.org/wiki/Q7075743","display_name":"Occupancy","level":2,"score":0.8365022540092468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6946308612823486},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5819199085235596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5369837880134583},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40087807178497314},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12276908755302429},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08645427227020264},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.06106686592102051},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4300000071525574}],"awards":[],"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":51,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2565639579","https://openalex.org/W2742332513","https://openalex.org/W2781228439","https://openalex.org/W2896704645","https://openalex.org/W2985775862","https://openalex.org/W2991216808","https://openalex.org/W3034868495","https://openalex.org/W3035308182","https://openalex.org/W3035564946","https://openalex.org/W3035574168","https://openalex.org/W3040145264","https://openalex.org/W3093922502","https://openalex.org/W3096390127","https://openalex.org/W3098650412","https://openalex.org/W3104876774","https://openalex.org/W3109395584","https://openalex.org/W3126856052","https://openalex.org/W3145284865","https://openalex.org/W3174692508","https://openalex.org/W3198451673","https://openalex.org/W3203158837","https://openalex.org/W3203597819","https://openalex.org/W3215023725","https://openalex.org/W3215584334","https://openalex.org/W4214530037","https://openalex.org/W4224436704","https://openalex.org/W4226305814","https://openalex.org/W4226339983","https://openalex.org/W4312349930","https://openalex.org/W4312641958","https://openalex.org/W4312793957","https://openalex.org/W4312894406","https://openalex.org/W4382464460","https://openalex.org/W4382466775","https://openalex.org/W4383097607","https://openalex.org/W4383108371","https://openalex.org/W4383109207","https://openalex.org/W4385259380","https://openalex.org/W4386066358","https://openalex.org/W4386075718","https://openalex.org/W4386076222","https://openalex.org/W4386083035","https://openalex.org/W4390873564","https://openalex.org/W4390874310","https://openalex.org/W6772033386","https://openalex.org/W6784094891","https://openalex.org/W6810381225","https://openalex.org/W6811230113"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"Monocular":[0],"Semantic":[1],"Occupancy":[2],"Prediction":[3],"aims":[4],"to":[5,27,30,51,121,133,158],"infer":[6],"the":[7,32,62,69,80,83,108,122,126,159,179],"complete":[8],"3D":[9,33,53],"geometry":[10],"and":[11,68,85,93,128,140,150,186],"semantic":[12,117,161],"information":[13,50,149],"of":[14,35,71,82,125,168],"scenes":[15],"from":[16,153],"only":[17],"2D":[18],"images.":[19],"It":[20],"has":[21],"garnered":[22],"significant":[23],"attention,":[24],"particularly":[25,90],"due":[26],"its":[28],"potential":[29],"enhance":[31],"perception":[34],"autonomous":[36],"vehicles.":[37],"However,":[38],"existing":[39],"methods":[40],"rely":[41],"on":[42,58,61,178],"a":[43,56,72,143,154],"complex":[44],"cascaded":[45],"framework":[46,84,112,127,164],"with":[47,137,165],"relatively":[48],"limited":[49],"restore":[52],"scenes,":[54],"including":[55],"dependency":[57],"supervision":[59,120],"solely":[60],"whole":[63],"network\u2019s":[64],"output,":[65],"single-frame":[66],"input,":[67],"utilization":[70],"small":[73],"backbone.":[74],"These":[75],"challenges,":[76],"in":[77],"turn,":[78],"hinder":[79],"optimization":[81],"yield":[86],"inferior":[87],"prediction":[88,111,163],"results,":[89],"concerning":[91],"smaller":[92],"long-tailed":[94],"objects.":[95],"To":[96],"address":[97],"these":[98,171],"issues,":[99],"we":[100,105],"propose":[101],"MonoOcc.":[102],"In":[103],"particular,":[104],"(i)":[106],"improve":[107],"monocular":[109,160],"occupancy":[110,162],"by":[113],"proposing":[114],"an":[115,129],"auxiliary":[116],"loss":[118],"as":[119],"shallow":[123],"layers":[124],"image-conditioned":[130],"cross-attention":[131],"module":[132,145],"refine":[134],"voxel":[135],"features":[136],"visual":[138],"clues,":[139],"(ii)":[141],"employ":[142],"distillation":[144],"that":[146],"transfers":[147],"temporal":[148],"richer":[151],"knowledge":[152],"larger":[155],"image":[156],"backbone":[157],"low":[166],"cost":[167],"hardware.":[169],"With":[170],"advantages,":[172],"our":[173],"method":[174],"yields":[175],"state-of-the-art":[176],"performance":[177],"camera-based":[180],"SemanticKITTI":[181],"Scene":[182],"Completion":[183],"benchmark.":[184],"Codes":[185],"models":[187],"can":[188],"be":[189],"accessed":[190],"at":[191],"https://github.com/ucaszyp/MonoOcc.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}