{"id":"https://openalex.org/W4399073789","doi":"https://doi.org/10.1109/tcsvt.2024.3406401","title":"Real-Time 3D Visual Perception by Cross-Dimensional Refined Learning","display_name":"Real-Time 3D Visual Perception by Cross-Dimensional Refined Learning","publication_year":2024,"publication_date":"2024-05-28","ids":{"openalex":"https://openalex.org/W4399073789","doi":"https://doi.org/10.1109/tcsvt.2024.3406401"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3406401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3406401","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5052377688","display_name":"Ziyang Hong","orcid":"https://orcid.org/0000-0001-9096-1750"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Ziyang Hong","raw_affiliation_strings":["Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083640052","display_name":"C. Patrick Yue","orcid":"https://orcid.org/0000-0002-8725-8148"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"C. Patrick Yue","raw_affiliation_strings":["Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052377688"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.4854,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6149856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"34","issue":"10","first_page":"10326","last_page":"10338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.991599977016449,"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":0.991599977016449,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9800000190734863,"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/computer-science","display_name":"Computer science","score":0.7128324508666992},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5804384350776672},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5496857166290283},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5350742340087891},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46146729588508606},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.4577310383319855},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.33988624811172485},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10474735498428345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7128324508666992},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5804384350776672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5496857166290283},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5350742340087891},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46146729588508606},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.4577310383319855},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33988624811172485},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10474735498428345},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2024.3406401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3406401","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-138992","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-138992","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1987648924","https://openalex.org/W2032871891","https://openalex.org/W2140965591","https://openalex.org/W2194775991","https://openalex.org/W2471962767","https://openalex.org/W2563685048","https://openalex.org/W2565639579","https://openalex.org/W2573741489","https://openalex.org/W2594519801","https://openalex.org/W2795014656","https://openalex.org/W2922220370","https://openalex.org/W2962793285","https://openalex.org/W2963125977","https://openalex.org/W2963627347","https://openalex.org/W2963918968","https://openalex.org/W2964009301","https://openalex.org/W2964032623","https://openalex.org/W2982169158","https://openalex.org/W3004300126","https://openalex.org/W3006536754","https://openalex.org/W3035003562","https://openalex.org/W3035015838","https://openalex.org/W3090386798","https://openalex.org/W3109428934","https://openalex.org/W3109585842","https://openalex.org/W3127555982","https://openalex.org/W3134684811","https://openalex.org/W3138270694","https://openalex.org/W3154129649","https://openalex.org/W3172610252","https://openalex.org/W3172717135","https://openalex.org/W3174525923","https://openalex.org/W3178217626","https://openalex.org/W3192398360","https://openalex.org/W3215584334","https://openalex.org/W3216000336","https://openalex.org/W4200074884","https://openalex.org/W4210961870","https://openalex.org/W4213438302","https://openalex.org/W4226275183","https://openalex.org/W4226416753","https://openalex.org/W4230575152","https://openalex.org/W4233857083","https://openalex.org/W4312601813","https://openalex.org/W4318829201","https://openalex.org/W4361997638","https://openalex.org/W4366148252","https://openalex.org/W4375797178","https://openalex.org/W4376851264","https://openalex.org/W4385245566","https://openalex.org/W4385318467","https://openalex.org/W4390190672","https://openalex.org/W4390872491","https://openalex.org/W4390873309","https://openalex.org/W4390874076","https://openalex.org/W4390874620","https://openalex.org/W4402733575","https://openalex.org/W6757817989","https://openalex.org/W6798491912","https://openalex.org/W6839182500","https://openalex.org/W6853534422"],"related_works":["https://openalex.org/W1897960459","https://openalex.org/W2002567531","https://openalex.org/W243736014","https://openalex.org/W2033349420","https://openalex.org/W4318185075","https://openalex.org/W2964529313","https://openalex.org/W1974005862","https://openalex.org/W2984197669","https://openalex.org/W2137629594","https://openalex.org/W2364416416"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,18,37,65,77,135,158],"novel":[3],"learning":[4,104],"method":[5,173],"that":[6,79,114,146,171],"can":[7,120,147,215],"effectively":[8],"perceive":[9],"both":[10,149],"the":[11,44,58,81,103,108,125,150,194,201,219],"geometry":[12],"structure":[13],"and":[14,153,183,189,213],"semantic":[15,128,132,155,187],"labels":[16],"of":[17,67,105,127,157,204],"3D":[19,26,45,151,154,176,186],"scene":[20,27,159],"in":[21,57,64,86,107,160,185],"real":[22,161],"time.":[23,162],"Existing":[24],"real-time":[25],"reconstruction":[28,191],"approaches":[29,50],"often":[30,62],"rely":[31],"on":[32,53,166,218],"volumetric":[33,49],"schemes":[34],"to":[35,101,124],"regress":[36],"Truncated":[38],"Signed":[39],"Distance":[40],"Function":[41],"(TSDF)":[42],"as":[43],"representation.":[46],"However,":[47],"these":[48],"primarily":[51],"focus":[52],"ensuring":[54],"global":[55],"coherence":[56],"reconstructed":[59],"scene,":[60],"which":[61,98],"results":[63,199],"lack":[66],"local":[68],"geometric":[69,83,190],"detail.":[70],"To":[71],"address":[72],"this":[73,115],"limitation,":[74],"we":[75,112,137,169],"propose":[76,138],"solution":[78],"leverages":[80],"latent":[82],"knowledge":[84],"present":[85],"2D":[87],"image":[88],"features":[89],"by":[90,130,179],"explicit":[91],"depth":[92],"prediction":[93],"thereby":[94],"creating":[95],"anchored":[96],"features,":[97],"are":[99],"used":[100],"refine":[102],"occupancy":[106],"TSDF":[109],"volume.":[110],"Furthermore,":[111],"discover":[113],"cross-dimensional":[116,141],"feature":[117],"refinement":[118,142],"methodology":[119],"also":[121],"be":[122,216],"applied":[123],"task":[126],"segmentation":[129,188],"utilizing":[131],"priors.":[133],"As":[134],"result,":[136],"an":[139],"end-to-end":[140],"neural":[143],"network":[144],"(CDRNet)":[145],"extract":[148],"mesh":[152],"labeling":[156],"Through":[163],"experimental":[164],"evaluation":[165],"multiple":[167],"datasets,":[168],"demonstrate":[170],"our":[172,205],"achieves":[174],"state-of-the-art":[175],"perception":[177],"capability":[178],"boosting":[180],"over":[181,193],"40%":[182],"18%":[184],"respectively":[192],"prior":[195],"art.":[196],"These":[197],"promising":[198],"indicate":[200],"significant":[202],"potential":[203],"approach":[206],"for":[207],"various":[208],"industrial":[209],"applications.":[210],"Demo":[211],"video":[212],"code":[214],"found":[217],"project":[220],"page,":[221],"https://hafred.github.io/cdrnet/.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}