{"id":"https://openalex.org/W4401416428","doi":"https://doi.org/10.1109/icra57147.2024.10610570","title":"Implicit Coarse-to-Fine 3D Perception for Category-level Object Pose Estimation from Monocular RGB Image","display_name":"Implicit Coarse-to-Fine 3D Perception for Category-level Object Pose Estimation from Monocular RGB Image","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416428","doi":"https://doi.org/10.1109/icra57147.2024.10610570"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610570","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":"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/A5005553164","display_name":"Jia Li","orcid":"https://orcid.org/0000-0002-8594-8356"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jia Li","raw_affiliation_strings":["School of Software, Shandong University,P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University,P.R. China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781249","display_name":"Jin Li","orcid":"https://orcid.org/0000-0002-0260-3169"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Jin","raw_affiliation_strings":["School of Software, Shandong University,P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University,P.R. China","institution_ids":["https://openalex.org/I154099455"]}]},{"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":["XR Vision Labs,Tencent,P.R. China"],"affiliations":[{"raw_affiliation_string":"XR Vision Labs,Tencent,P.R. China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081760619","display_name":"Yeheng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yeheng Chen","raw_affiliation_strings":["Intelligent Robot Research Center, Zhejiang Lab,P.R. China"],"affiliations":[{"raw_affiliation_string":"Intelligent Robot Research Center, Zhejiang Lab,P.R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341119","display_name":"Nan Li","orcid":"https://orcid.org/0000-0003-3585-2273"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Li","raw_affiliation_strings":["Intelligent Robot Research Center, Zhejiang Lab,P.R. China"],"affiliations":[{"raw_affiliation_string":"Intelligent Robot Research Center, Zhejiang Lab,P.R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008274291","display_name":"Xueying Qin","orcid":"https://orcid.org/0000-0003-0057-295X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueying Qin","raw_affiliation_strings":["School of Software, Shandong University,P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University,P.R. China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005553164"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.3488,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57255974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2043","last_page":"2050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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":0.9997000098228455,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9943000078201294,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9911999702453613,"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":0.7952538728713989},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7942023277282715},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.7576747536659241},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6377815008163452},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.632235586643219},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5835913419723511},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.542169988155365},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5222631096839905},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.48062580823898315},{"id":"https://openalex.org/keywords/depth-perception","display_name":"Depth perception","score":0.4188733398914337},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4101666808128357},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.125389963388443}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7952538728713989},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7942023277282715},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7576747536659241},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6377815008163452},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.632235586643219},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5835913419723511},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.542169988155365},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5222631096839905},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.48062580823898315},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.4188733398914337},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4101666808128357},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.125389963388443},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610570","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2200124539","https://openalex.org/W2781181706","https://openalex.org/W2963177347","https://openalex.org/W2963188159","https://openalex.org/W2963756608","https://openalex.org/W2963892972","https://openalex.org/W2963911235","https://openalex.org/W2981378444","https://openalex.org/W2990578762","https://openalex.org/W2998787775","https://openalex.org/W3034986117","https://openalex.org/W3035398346","https://openalex.org/W3090443815","https://openalex.org/W3090584485","https://openalex.org/W3107372911","https://openalex.org/W3107992529","https://openalex.org/W3127066163","https://openalex.org/W3163945288","https://openalex.org/W3196328566","https://openalex.org/W3202459445","https://openalex.org/W4226321491","https://openalex.org/W4312296985","https://openalex.org/W4312801317","https://openalex.org/W4312982499","https://openalex.org/W4313027996","https://openalex.org/W4323065906","https://openalex.org/W4386065651","https://openalex.org/W4386075656","https://openalex.org/W4390873470","https://openalex.org/W6739778489"],"related_works":["https://openalex.org/W4253893311","https://openalex.org/W3089306886","https://openalex.org/W2074216034","https://openalex.org/W2113785214","https://openalex.org/W2798721181","https://openalex.org/W3201205132","https://openalex.org/W4312694060","https://openalex.org/W4386075737","https://openalex.org/W4307623796","https://openalex.org/W4394784820"],"abstract_inverted_index":{"Category-level":[0],"object":[1],"pose":[2,45,65,98],"estimation":[3,46,66],"demonstrates":[4],"robust":[5],"generalization":[6],"capabilities":[7],"that":[8,80,109],"benefit":[9],"robotics":[10],"applications.":[11],"However,":[12],"exclusive":[13],"reliance":[14],"on":[15,97,104,115,119,121],"RGB":[16,50,73],"images":[17],"without":[18],"leveraging":[19],"any":[20],"3D":[21,88],"information":[22],"introduces":[23],"ambiguity":[24,71],"in":[25,52],"the":[26,69,94,122,127],"translation":[27],"and":[28,91,99,106,117,129],"size":[29,100],"of":[30,72],"objects,":[31],"leading":[32],"to":[33,85],"suboptimal":[34],"performance.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39,75],"propose":[40],"a":[41,48,77],"framework":[42],"for":[43],"category-level":[44],"from":[47],"single":[49],"image":[51],"an":[53],"end-to-end":[54],"manner,":[55],"i.e.,":[56],"Feature":[57],"Auxiliary":[58],"Perception":[59],"Network":[60],"(FAP-Net).":[61],"To":[62],"address":[63],"inaccurate":[64],"caused":[67],"by":[68],"inherent":[70],"images,":[74],"design":[76],"coarse-to-fine":[78],"approach":[79],"first":[81],"harnesses":[82],"geometry":[83],"supervision":[84],"facilitate":[86],"coarse":[87],"feature":[89],"perception":[90],"subsequently":[92],"refines":[93],"features":[95],"based":[96],"constraints.":[101],"Experimental":[102],"results":[103],"REAL275":[105,124],"CAMERA25":[107],"demonstrate":[108],"FAP-Net":[110],"achieves":[111],"significant":[112],"improvements":[113],"(14.7%":[114],"10\u00b010cm":[116],"11.4%":[118],"IoU50":[120],"real-scene":[123],"dataset)":[125],"over":[126],"state-of-the-art":[128],"real-time":[130],"inference":[131],"(42":[132],"FPS).":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}