{"id":"https://openalex.org/W4383109669","doi":"https://doi.org/10.1109/icra48891.2023.10160780","title":"StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCS","display_name":"StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCS","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383109669","doi":"https://doi.org/10.1109/icra48891.2023.10160780"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100437922","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0001-5727-385X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101652979","display_name":"Stephen James","orcid":"https://orcid.org/0000-0002-3991-0621"},"institutions":[{"id":"https://openalex.org/I4210106410","display_name":"Vysok\u00e1 \u0160kola Realitn\u00ed Institut Franka Dysona","ror":"https://ror.org/01mpgt112","country_code":"CZ","type":"education","lineage":["https://openalex.org/I4210106410"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["CZ","US"],"is_corresponding":false,"raw_author_name":"Stephen James","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley","Dyson Robot Learning Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Dyson Robot Learning Lab","institution_ids":["https://openalex.org/I4210106410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007088651","display_name":"Congying Sui","orcid":"https://orcid.org/0000-0002-0796-2689"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Congying Sui","raw_affiliation_strings":["Hong Kong Centre for Logistics Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Centre for Logistics Robotics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707660","display_name":"Yunhui Liu","orcid":"https://orcid.org/0000-0002-3625-6679"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yun-Hui Liu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090516040","display_name":"Qi Dou","orcid":"https://orcid.org/0000-0002-3416-9950"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qi Dou","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2855","last_page":"2861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9986000061035156,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10036","display_name":"Advanced Neural Network Applications","score":0.9919000267982483,"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/pose","display_name":"Pose","score":0.8824642896652222},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7803525924682617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7798133492469788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7757662534713745},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6950820088386536},{"id":"https://openalex.org/keywords/epipolar-geometry","display_name":"Epipolar geometry","score":0.6155155897140503},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.5321126580238342},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5210106372833252},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.48171931505203247},{"id":"https://openalex.org/keywords/stereo-cameras","display_name":"Stereo cameras","score":0.4148169159889221},{"id":"https://openalex.org/keywords/stereopsis","display_name":"Stereopsis","score":0.301513671875},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16720682382583618}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8824642896652222},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7803525924682617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7798133492469788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7757662534713745},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6950820088386536},{"id":"https://openalex.org/C23379248","wikidata":"https://www.wikidata.org/wiki/Q200904","display_name":"Epipolar geometry","level":3,"score":0.6155155897140503},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.5321126580238342},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5210106372833252},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.48171931505203247},{"id":"https://openalex.org/C35861506","wikidata":"https://www.wikidata.org/wiki/Q17141434","display_name":"Stereo cameras","level":3,"score":0.4148169159889221},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.301513671875},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16720682382583618}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1991544872","https://openalex.org/W2006199805","https://openalex.org/W2033819227","https://openalex.org/W2085261163","https://openalex.org/W2194775991","https://openalex.org/W2413354348","https://openalex.org/W2560023338","https://openalex.org/W2885546722","https://openalex.org/W2921849174","https://openalex.org/W2963756608","https://openalex.org/W2963892972","https://openalex.org/W3034597466","https://openalex.org/W3035235920","https://openalex.org/W3089874271","https://openalex.org/W3107634219","https://openalex.org/W3107785885","https://openalex.org/W3107992529","https://openalex.org/W3109733326","https://openalex.org/W3171847116","https://openalex.org/W3175560234","https://openalex.org/W3193686508","https://openalex.org/W3201833577","https://openalex.org/W3202459445","https://openalex.org/W3206803482","https://openalex.org/W3208372443","https://openalex.org/W3214000333","https://openalex.org/W3216621076","https://openalex.org/W4200492212","https://openalex.org/W4205105995","https://openalex.org/W4226321491","https://openalex.org/W4226322645","https://openalex.org/W4235232193","https://openalex.org/W4285190019","https://openalex.org/W4285505783","https://openalex.org/W4312266040","https://openalex.org/W4312296985","https://openalex.org/W4312344659","https://openalex.org/W4312601209","https://openalex.org/W4312604533","https://openalex.org/W4312818087","https://openalex.org/W4312877043","https://openalex.org/W4313027996","https://openalex.org/W6753335413","https://openalex.org/W6775857102","https://openalex.org/W6780515072","https://openalex.org/W6801427515","https://openalex.org/W6802704039","https://openalex.org/W6804361632","https://openalex.org/W6810816294","https://openalex.org/W6816408058"],"related_works":["https://openalex.org/W2113785214","https://openalex.org/W2946083937","https://openalex.org/W2088028039","https://openalex.org/W2798721181","https://openalex.org/W4386075737","https://openalex.org/W1974260915","https://openalex.org/W4382141741","https://openalex.org/W128884630","https://openalex.org/W4299867837","https://openalex.org/W2951583186"],"abstract_inverted_index":{"Most":[0],"existing":[1,39],"methods":[2,40],"for":[3,61,68,128,157,179,187,210],"category-level":[4,62,85,211],"pose":[5,64,86,93,96,102,160,215],"estimation":[6,74,87],"rely":[7],"on":[8,104,150,197,223],"object":[9,63,89,101,109,156,214],"point":[10,29,37],"clouds.":[11],"However,":[12],"when":[13],"considering":[14],"transparent":[15,46,69,130,155,213],"objects,":[16],"depth":[17],"cameras":[18],"are":[19,41],"usually":[20],"not":[21,42],"able":[22],"to":[23,44,136],"capture":[24],"high-quality":[25],"data,":[26],"resulting":[27],"in":[28,106],"clouds":[30],"with":[31,174],"severe":[32],"artifacts.":[33],"Without":[34],"a":[35,55,72,81,124,175],"complete":[36],"cloud,":[38],"applicable":[43],"challenging":[45],"objects.":[47,70],"To":[48,113,162],"tackle":[49],"this":[50],"problem,":[51],"we":[52,79,121],"present":[53],"StereoPose,":[54],"novel":[56],"stereo":[57,77,169,180],"image":[58,118],"based":[59,103],"framework":[60,209],"estimation,":[65,91,94],"ideally":[66],"suited":[67],"For":[71],"robust":[73],"from":[75],"pure":[76],"images,":[78],"develop":[80],"pipeline":[82],"that":[83],"decouples":[84],"into":[88],"size":[90],"initial":[92],"and":[95,146,183,218],"refinement.":[97],"StereoPose":[98,171,208],"then":[99],"estimates":[100],"representation":[105],"the":[107,115,129,138,151,154,165,168,189,198,203,206,224],"normalized":[108],"coordinate":[110],"space":[111],"(NOCS).":[112],"address":[114],"issue":[116],"of":[117,153,167,192,205],"content":[119,144],"aliasing,":[120,145],"further":[122,163],"define":[123],"back-view":[125,133],"NOCS":[126,134],"map":[127],"object.":[131],"The":[132],"aims":[135],"reduce":[137],"network":[139,193],"learning":[140],"ambiguity":[141],"caused":[142],"by":[143],"leverage":[147],"informative":[148],"cues":[149],"back":[152],"more":[158],"accurate":[159],"estimation.":[161,216],"improve":[164],"performance":[166],"framework,":[170],"is":[172],"equipped":[173],"parallax":[176],"attention":[177],"module":[178],"feature":[181],"fusion":[182],"an":[184],"epipolar":[185],"loss":[186],"improving":[188],"stereo-view":[190],"consistency":[191],"predictions.":[194],"Extensive":[195],"experiments":[196],"public":[199],"TOD":[200],"dataset":[201],"demonstrate":[202],"superiority":[204],"proposed":[207],"6D":[212],"Code":[217],"demos":[219],"will":[220],"be":[221],"available":[222],"project":[225],"homepage:":[226],"www.cse.cuhk.edu.hk/~kaichen/stereopose.html.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}