{"id":"https://openalex.org/W4401416926","doi":"https://doi.org/10.1109/icra57147.2024.10611723","title":"RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery","display_name":"RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416926","doi":"https://doi.org/10.1109/icra57147.2024.10611723"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611723","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":"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/A5030033238","display_name":"Jiaxin Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Jiaxin Wei","raw_affiliation_strings":["Technical University of Munich,Smart Robotics Lab, CIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Smart Robotics Lab, CIT","institution_ids":["https://openalex.org/I4210116723","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030165903","display_name":"Xibin Song","orcid":"https://orcid.org/0000-0001-7019-6238"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xibin Song","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063856911","display_name":"Weizhe Liu","orcid":"https://orcid.org/0000-0003-3762-7344"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhe Liu","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044711470","display_name":"Laurent Kneip","orcid":"https://orcid.org/0000-0001-6727-6608"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Laurent Kneip","raw_affiliation_strings":["ShanghaiTech University,Mobile Perception Lab, SIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,Mobile Perception Lab, SIST","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101819061","display_name":"Hongdong Li","orcid":"https://orcid.org/0000-0003-4125-1554"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hongdong Li","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063587709","display_name":"Pan Ji","orcid":"https://orcid.org/0000-0001-6213-554X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Ji","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2036","last_page":"2042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9976000189781189,"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/metric","display_name":"Metric (unit)","score":0.6474598050117493},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6425555944442749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6348977088928223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6140437126159668},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.579361081123352},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5522862076759338},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4940372109413147},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4449451267719269},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1264212429523468},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11817294359207153},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.05775001645088196}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6474598050117493},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6425555944442749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6348977088928223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6140437126159668},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.579361081123352},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5522862076759338},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4940372109413147},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4449451267719269},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1264212429523468},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11817294359207153},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.05775001645088196},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra57147.2024.10611723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611723","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"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/733751679","is_oa":false,"landing_page_url":"https://hdl.handle.net/1885/733751679","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2128019145","https://openalex.org/W2194775991","https://openalex.org/W2560023338","https://openalex.org/W2963121255","https://openalex.org/W2963150697","https://openalex.org/W2963892972","https://openalex.org/W2998787775","https://openalex.org/W3034597466","https://openalex.org/W3039645397","https://openalex.org/W3056171435","https://openalex.org/W3084902463","https://openalex.org/W3104104643","https://openalex.org/W3107372911","https://openalex.org/W3107992529","https://openalex.org/W3163945288","https://openalex.org/W3193686508","https://openalex.org/W3195196013","https://openalex.org/W3196328566","https://openalex.org/W3202459445","https://openalex.org/W3202538459","https://openalex.org/W3203887644","https://openalex.org/W4214520160","https://openalex.org/W4226321491","https://openalex.org/W4293374772","https://openalex.org/W4312296985","https://openalex.org/W4312339117","https://openalex.org/W4312388311","https://openalex.org/W4312604533","https://openalex.org/W4312801317","https://openalex.org/W4385814207","https://openalex.org/W6739778489","https://openalex.org/W6743668622","https://openalex.org/W6783432159"],"related_works":["https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W4387967917","https://openalex.org/W4386925306","https://openalex.org/W4387968151","https://openalex.org/W3132124459","https://openalex.org/W2946083937","https://openalex.org/W2894986065","https://openalex.org/W4299867837","https://openalex.org/W3110557940"],"abstract_inverted_index":{"While":[0],"showing":[1],"promising":[2],"results,":[3],"recent":[4],"RGB-D":[5],"camera-based":[6],"category-level":[7,104],"object":[8,101,118],"pose":[9,53],"estimation":[10,56],"methods":[11,24],"have":[12,122],"restricted":[13],"applications":[14],"due":[15],"to":[16,28,57,74,93,113],"the":[17,51,59,81,96,100,110,132],"heavy":[18],"reliance":[19],"on":[20,64,103,125],"depth":[21],"sensors.":[22],"RGB-only":[23],"provide":[25],"an":[26],"alternative":[27],"this":[29,42],"problem":[30],"yet":[31],"suffer":[32],"from":[33,38],"inherent":[34],"scale":[35,98],"ambiguity":[36],"stemming":[37],"monocular":[39,72],"observations.":[40],"In":[41],"paper,":[43],"we":[44,68,107],"propose":[45],"a":[46,70,88],"novel":[47],"pipeline":[48],"that":[49],"decouples":[50],"6D":[52,117],"and":[54,128],"size":[55],"mitigate":[58],"influence":[60],"of":[61,99,135,146],"imperfect":[62],"scales":[63],"rigid":[65],"transformations.":[66],"Specifically,":[67],"leverage":[69],"pre-trained":[71],"estimator":[73],"extract":[75],"local":[76],"geometric":[77],"information,":[78],"mainly":[79],"facilitating":[80],"search":[82],"for":[83,116],"inlier":[84],"2D-3D":[85],"correspondence.":[86],"Meanwhile,":[87],"separate":[89],"branch":[90],"is":[91],"designed":[92],"directly":[94],"recover":[95],"metric":[97],"based":[102],"statistics.":[105],"Finally,":[106],"advocate":[108],"using":[109],"RANSAC-PnP":[111],"algorithm":[112],"robustly":[114],"solve":[115],"pose.":[119],"Extensive":[120],"experiments":[121],"been":[123],"conducted":[124],"both":[126],"synthetic":[127],"real":[129],"datasets,":[130],"demonstrating":[131],"superior":[133],"performance":[134],"our":[136],"method":[137],"over":[138],"previous":[139],"state-of-the-art":[140],"RGB-based":[141],"approaches,":[142],"especially":[143],"in":[144],"terms":[145],"rotation":[147],"accuracy.":[148],"Code:":[149],"https://github.com/goldoak/DMSR.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}