{"id":"https://openalex.org/W4409326469","doi":"https://doi.org/10.1109/lra.2025.3559841","title":"RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement","display_name":"RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement","publication_year":2025,"publication_date":"2025-04-10","ids":{"openalex":"https://openalex.org/W4409326469","doi":"https://doi.org/10.1109/lra.2025.3559841"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3559841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3559841","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5112361483","display_name":"Hui Yang","orcid":"https://orcid.org/0009-0005-2648-9566"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Yang","raw_affiliation_strings":["National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China","National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, China"],"raw_orcid":"https://orcid.org/0009-0005-2648-9566","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, China","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Sun","orcid":"https://orcid.org/0000-0002-8644-2998"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Sun","raw_affiliation_strings":["National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China","National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, China"],"raw_orcid":"https://orcid.org/0000-0002-8644-2998","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, China","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108049455","display_name":"Jian Liu","orcid":"https://orcid.org/0000-0003-0604-8024"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Liu","raw_affiliation_strings":["National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China","National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, China"],"raw_orcid":"https://orcid.org/0000-0003-0604-8024","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, China","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015511443","display_name":"Jin Zheng","orcid":"https://orcid.org/0000-0003-3353-1775"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Zheng","raw_affiliation_strings":["School of Architecture and Art, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3353-1775","affiliations":[{"raw_affiliation_string":"School of Architecture and Art, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiwen Zeng","orcid":"https://orcid.org/0009-0006-2369-1491"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwen Zeng","raw_affiliation_strings":["National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China","National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, China"],"raw_orcid":"https://orcid.org/0009-0006-2369-1491","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, China","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089986388","display_name":"Ajmal Mian","orcid":"https://orcid.org/0000-0002-5206-3842"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ajmal Mian","raw_affiliation_strings":["Department of Computer Science and Software Engineering, University of Western Australia, Crawley, WA, Australia","Department of Computer Science and Software Engineering, The University of Western Australia, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5206-3842","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, University of Western Australia, Crawley, WA, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7946,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69523236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"10","issue":"6","first_page":"5377","last_page":"5384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9984999895095825,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9984999895095825,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9976000189781189,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9926000237464905,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6703506112098694},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6591514945030212},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.630896806716919},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5999038815498352},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5678736567497253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.536318838596344},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5179242491722107},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35804176330566406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32345128059387207},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1009913980960846}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6703506112098694},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6591514945030212},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.630896806716919},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5999038815498352},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5678736567497253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.536318838596344},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5179242491722107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35804176330566406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32345128059387207},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1009913980960846},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2025.3559841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3559841","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/65bed4ac-3ccf-402d-927a-9bfd0fceb26c","is_oa":false,"landing_page_url":"https://admin.research-repository.uwa.edu.au/en/publications/65bed4ac-3ccf-402d-927a-9bfd0fceb26c","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Yang, H, Sun, W, Liu, J, Zheng, J, Zeng, Z & Mian, A 2025, 'RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement', IEEE Robotics and Automation Letters, vol. 10, no. 6, pp. 5377-5384. https://doi.org/10.1109/LRA.2025.3559841","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G1201409244","display_name":null,"funder_award_id":"62473141","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2187632043","display_name":null,"funder_award_id":"2024JJ5098","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G3206439402","display_name":null,"funder_award_id":"FT210100268","funder_id":"https://openalex.org/F4320315885","funder_display_name":"Australian Government"},{"id":"https://openalex.org/G3408348127","display_name":null,"funder_award_id":"U22A2059","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2555618208","https://openalex.org/W2963150697","https://openalex.org/W2963892972","https://openalex.org/W2987741655","https://openalex.org/W2988766935","https://openalex.org/W3090584485","https://openalex.org/W3093644825","https://openalex.org/W3107372911","https://openalex.org/W3107992529","https://openalex.org/W3164543136","https://openalex.org/W3193686508","https://openalex.org/W3196328566","https://openalex.org/W3199947443","https://openalex.org/W3202459445","https://openalex.org/W3206934897","https://openalex.org/W4205105995","https://openalex.org/W4226321491","https://openalex.org/W4226409831","https://openalex.org/W4285221346","https://openalex.org/W4285233964","https://openalex.org/W4312491686","https://openalex.org/W4312777209","https://openalex.org/W4312801317","https://openalex.org/W4313156423","https://openalex.org/W4321033239","https://openalex.org/W4323065906","https://openalex.org/W4366148220","https://openalex.org/W4386065760","https://openalex.org/W4386075656","https://openalex.org/W4390190260","https://openalex.org/W4390872672","https://openalex.org/W4390873470","https://openalex.org/W4391855168","https://openalex.org/W4392979363","https://openalex.org/W4400726600","https://openalex.org/W4401416926","https://openalex.org/W4402727359","https://openalex.org/W4402916825","https://openalex.org/W4403779064","https://openalex.org/W6850630192","https://openalex.org/W6851800889","https://openalex.org/W6852690433"],"related_works":["https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W4387967917","https://openalex.org/W4387968151","https://openalex.org/W4386925306","https://openalex.org/W3132124459","https://openalex.org/W2946083937","https://openalex.org/W3101088080","https://openalex.org/W2894986065","https://openalex.org/W4299867837"],"abstract_inverted_index":{"Category-level":[0],"pose":[1,53,65],"estimation":[2,66,214],"methods":[3,20,33,44],"have":[4,21],"received":[5],"widespread":[6],"attention":[7],"as":[8],"they":[9],"can":[10],"be":[11],"generalized":[12],"to":[13,51,75,97,118,142,223],"intra-class":[14],"unseen":[15],"objects.":[16,229],"Although":[17],"RGB-D-based":[18],"category-level":[19,63],"made":[22],"significant":[23],"progress,":[24],"reliance":[25],"on":[26,93,200],"depth":[27,57,80,103,127,147],"image":[28,85,148],"limits":[29],"practical":[30,37],"application.":[31],"RGB-based":[32,43],"offer":[34],"a":[35,68,114,172,187],"more":[36,188],"and":[38,59,86,104,129,149,162,171,174,195,203,215,227],"cost-effective":[39],"solution.":[40],"However,":[41],"current":[42],"struggle":[45],"with":[46],"object":[47,64],"geometry":[48],"perception,":[49],"leading":[50],"inaccurate":[52],"estimation.":[54],"We":[55,72,112],"propose":[56,87],"recovery":[58],"adaptive":[60,89],"refinement":[61,90],"for":[62,179],"from":[67,81,108,126,157],"single":[69],"RGB":[70,84],"image.":[71,135],"leverage":[73],"DINOv2":[74],"reconstruct":[76],"the":[77,82,100,109,122,130,133,140,146,150,158,183,201,207],"coarse":[78,102],"scene-level":[79],"input":[83],"an":[88,94],"network":[91],"based":[92],"encoder-decoder":[95],"architecture":[96],"dynamically":[98],"improve":[99],"predicted":[101],"reduce":[105],"its":[106],"gap":[107],"ground":[110],"truth.":[111],"introduce":[113],"2D-3D":[115],"consistency":[116,137],"loss":[117],"ensure":[119],"correspondence":[120],"between":[121,145],"point":[123,151,160],"cloud":[124,161],"obtained":[125],"projection":[128],"objects":[131],"in":[132],"2D":[134],"This":[136],"supervision":[138],"enables":[139],"model":[141,221],"maintain":[143],"alignment":[144],"cloud.":[152],"Finally,":[153],"we":[154],"extract":[155],"features":[156],"refined":[159],"feed":[163],"them":[164],"into":[165],"two":[166],"confidence-aware":[167],"rotation":[168,184],"regression":[169],"branches":[170],"translation":[173],"size":[175],"prediction":[176],"residual":[177],"branch":[178],"end-to-end":[180],"training.":[181],"Decoupling":[182],"matrix":[185],"provides":[186],"direct":[189],"representation,":[190],"which":[191],"facilitates":[192],"parameter":[193],"optimization":[194],"gradient":[196],"propagation.":[197],"Extensive":[198],"experiments":[199,218],"REAL275":[202],"CAMERA25":[204],"datasets":[205],"demonstrate":[206,219],"superior":[208],"performance":[209],"of":[210],"our":[211,220],"method.":[212],"Real-world":[213],"robotic":[216],"grasping":[217],"robustness":[222],"occlusion,":[224],"clutter":[225],"environments,":[226],"low-textured":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}