{"id":"https://openalex.org/W7117148086","doi":"https://doi.org/10.1109/tip.2025.3635475","title":"Enhanced Geometry and Semantics for Camera-Based 3D Semantic Scene Completion","display_name":"Enhanced Geometry and Semantics for Camera-Based 3D Semantic Scene Completion","publication_year":2025,"publication_date":"2025-12-24","ids":{"openalex":"https://openalex.org/W7117148086","doi":"https://doi.org/10.1109/tip.2025.3635475","pmid":"https://pubmed.ncbi.nlm.nih.gov/41442293"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3635475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3635475","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5121227015","display_name":"Haihong Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haihong Xiao","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114334171","display_name":"Wenxiong Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxiong Kang","raw_affiliation_strings":["School of Automation Science and Engineering and the School of Future Technology, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Engineering and the School of Future Technology, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013644792","display_name":"Yulan Guo","orcid":"https://orcid.org/0000-0003-0952-476X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulan Guo","raw_affiliation_strings":["School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019269584","display_name":"H. Y. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127658","display_name":"Ministry of Natural Resources","ror":"https://ror.org/03tk15k72","country_code":"RW","type":"government","lineage":["https://openalex.org/I4210127658"]}],"countries":["RW"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["School of Geospatial Artificial Intelligence, the Key Laboratory of Geographic Information Science (Ministry of Education), and the Key Laboratory of Spatial-temporal Big Data Analysis and Application of Natural Resources in Megacities (Ministry of Natural Resources), East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Geospatial Artificial Intelligence, the Key Laboratory of Geographic Information Science (Ministry of Education), and the Key Laboratory of Spatial-temporal Big Data Analysis and Application of Natural Resources in Megacities (Ministry of Natural Resources), East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210127658"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008105605","display_name":"Y He","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ying He","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5121227015"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62675577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9182000160217285,"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":0.9182000160217285,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.019300000742077827,"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"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.017400000244379044,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6169000267982483},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5005000233650208},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.4632999897003174},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.45399999618530273},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.44279998540878296},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42089998722076416},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4163999855518341},{"id":"https://openalex.org/keywords/2d-to-3d-conversion","display_name":"2D to 3D conversion","score":0.40630000829696655},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.3831999897956848},{"id":"https://openalex.org/keywords/transformation-geometry","display_name":"Transformation geometry","score":0.34290000796318054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7560999989509583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.697700023651123},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6176000237464905},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5005000233650208},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.45399999618530273},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.44279998540878296},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C84824328","wikidata":"https://www.wikidata.org/wiki/Q4633097","display_name":"2D to 3D conversion","level":3,"score":0.40630000829696655},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C32990609","wikidata":"https://www.wikidata.org/wiki/Q306542","display_name":"Transformation geometry","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.32510000467300415},{"id":"https://openalex.org/C56435381","wikidata":"https://www.wikidata.org/wiki/Q1196371","display_name":"Geometric transformation","level":3,"score":0.3237999975681305},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.314300000667572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C193581530","wikidata":"https://www.wikidata.org/wiki/Q683778","display_name":"Structured light","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2025.3635475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3635475","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41442293","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41442293","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:dr.ntu.edu.sg:10356/212393","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/212393","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7321358919143677,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1122191357","display_name":null,"funder_award_id":"62376100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5775785410","display_name":null,"funder_award_id":"62476077","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5943813557","display_name":null,"funder_award_id":"62076086","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W2030300879","https://openalex.org/W2150066425","https://openalex.org/W2557465155","https://openalex.org/W2560609797","https://openalex.org/W2903435684","https://openalex.org/W2948515602","https://openalex.org/W2987505621","https://openalex.org/W2991216808","https://openalex.org/W3014859219","https://openalex.org/W3034868495","https://openalex.org/W3034961469","https://openalex.org/W3034968345","https://openalex.org/W3035308182","https://openalex.org/W3109395584","https://openalex.org/W3126856052","https://openalex.org/W3155390614","https://openalex.org/W3159481202","https://openalex.org/W3173727695","https://openalex.org/W3176973414","https://openalex.org/W3179909833","https://openalex.org/W3195680177","https://openalex.org/W3203597819","https://openalex.org/W3215023725","https://openalex.org/W3215584334","https://openalex.org/W4200150166","https://openalex.org/W4214684804","https://openalex.org/W4226420988","https://openalex.org/W4312641958","https://openalex.org/W4312662745","https://openalex.org/W4312790276","https://openalex.org/W4312894406","https://openalex.org/W4312960790","https://openalex.org/W4321232185","https://openalex.org/W4382464460","https://openalex.org/W4386065379","https://openalex.org/W4386066358","https://openalex.org/W4386075553","https://openalex.org/W4386075718","https://openalex.org/W4386083035","https://openalex.org/W4390492478","https://openalex.org/W4390872638","https://openalex.org/W4390872682","https://openalex.org/W4390873074","https://openalex.org/W4390873564","https://openalex.org/W4390874310","https://openalex.org/W4392719448","https://openalex.org/W4393153987","https://openalex.org/W4393154098","https://openalex.org/W4395471044","https://openalex.org/W4399574285","https://openalex.org/W4402703001","https://openalex.org/W4402705525","https://openalex.org/W4402715923","https://openalex.org/W4402716032","https://openalex.org/W4402726963","https://openalex.org/W4402727084","https://openalex.org/W4402727581","https://openalex.org/W4402753672","https://openalex.org/W4402753866","https://openalex.org/W4402772482","https://openalex.org/W4402891997","https://openalex.org/W4402951642","https://openalex.org/W4403947105","https://openalex.org/W4404005296","https://openalex.org/W4404725701","https://openalex.org/W4405219754","https://openalex.org/W4405429367","https://openalex.org/W4405785635","https://openalex.org/W4409365856","https://openalex.org/W4409370112","https://openalex.org/W4413145021","https://openalex.org/W4413156589"],"related_works":[],"abstract_inverted_index":{"Giving":[0],"machines":[1],"the":[2,6,69,90,136,146,152,173,198],"ability":[3],"to":[4,40,102,130,141,171],"infer":[5],"complete":[7],"3D":[8,36,127,140],"geometry":[9],"and":[10,24,48,143,167,178,201],"semantics":[11],"of":[12,92,148,154],"complex":[13],"scenes":[14],"is":[15],"crucial":[16],"for":[17],"many":[18],"downstream":[19],"tasks,":[20],"such":[21,61],"as":[22,33,62],"decision-making":[23],"planning.":[25],"Vision-centric":[26],"Semantic":[27],"Scene":[28],"Completion":[29],"(SSC)":[30],"has":[31],"emerged":[32],"a":[34,116,163,168],"trendy":[35],"perception":[37],"paradigm":[38],"due":[39],"its":[41],"compatibility":[42],"with":[43,109],"task":[44],"properties,":[45],"low":[46],"cost,":[47],"rich":[49],"visual":[50],"cues.":[51],"Despite":[52],"impressive":[53],"results,":[54],"current":[55],"approaches":[56],"inevitably":[57],"suffer":[58],"from":[59,139],"problems":[60],"depth":[63,66,94,104,111,117,132],"errors":[64],"or":[65],"ambiguities":[67,133],"during":[68],"2D-to-3D":[70],"transformation":[71],"process.":[72],"To":[73],"overcome":[74],"these":[75],"limitations,":[76],"in":[77,107,126],"this":[78],"paper,":[79],"we":[80,114,159],"first":[81],"introduce":[82],"an":[83],"Optical":[84],"Flow-Guided":[85],"(OFG)":[86],"DepthNet":[87],"that":[88,122],"leverages":[89],"strengths":[91],"pretrained":[93],"estimation":[95],"models,":[96],"while":[97],"incorporating":[98],"optical":[99],"flow":[100],"images":[101],"improve":[103],"prediction":[105,176],"accuracy":[106],"regions":[108],"significant":[110],"changes.":[112],"Then,":[113],"propose":[115],"ambiguity-mitigated":[118],"feature":[119,149],"lifting":[120],"strategy":[121],"implements":[123],"deformable":[124],"cross-attention":[125],"pixel":[128],"space":[129],"avoid":[131],"caused":[134],"by":[135],"projection":[137],"process":[138],"2D":[142],"further":[144],"enhances":[145],"effectiveness":[147],"updating":[150],"through":[151],"utilization":[153],"prior":[155],"mask":[156],"indices.":[157],"Moreover,":[158],"customize":[160],"two":[161],"subnetworks:":[162],"residual":[164],"voxel":[165],"network":[166],"sparse":[169],"UNet,":[170],"enhance":[172],"network's":[174],"geometric":[175],"capabilities":[177],"ensure":[179],"consistent":[180],"semantic":[181],"reasoning":[182],"across":[183],"varying":[184],"scales.":[185],"By":[186],"doing":[187],"so,":[188],"our":[189],"method":[190],"achieves":[191],"performance":[192],"improvements":[193],"over":[194],"state-of-the-art":[195],"methods":[196],"on":[197],"SemanticKITTI,":[199],"SSCBench-KITTI-360":[200],"Occ3D-nuScene":[202],"benchmarks.":[203]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-24T00:00:00"}