{"id":"https://openalex.org/W3206934897","doi":"https://doi.org/10.1109/tip.2022.3216980","title":"6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-Based Instance Representation Learning","display_name":"6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-Based Instance Representation Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3206934897","doi":"https://doi.org/10.1109/tip.2022.3216980","mag":"3206934897","pmid":"https://pubmed.ncbi.nlm.nih.gov/36315551"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3216980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3216980","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.04792","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103029465","display_name":"Lu Zou","orcid":"https://orcid.org/0000-0002-2619-3475"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lu Zou","raw_affiliation_strings":["School of Data Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Data Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017524281","display_name":"Zhangjin Huang","orcid":"https://orcid.org/0000-0003-1475-8894"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangjin Huang","raw_affiliation_strings":["School of Computer Science and Technology and the School of Data Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology and the School of Data Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084538628","display_name":"Naijie Gu","orcid":"https://orcid.org/0000-0002-8898-0896"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naijie Gu","raw_affiliation_strings":["School of Computer Science and Technology and the School of Data Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology and the School of Data Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115588322","display_name":"Guoping Wang","orcid":"https://orcid.org/0000-0001-7819-0076"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoping Wang","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103029465"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":6.4298,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.97353264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"6907","last_page":"6921"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9969000220298767,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.6845612525939941},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6456264853477478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6013288497924805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5379498600959778},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5183306932449341},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5172017812728882},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.43635135889053345},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4328545331954956},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.42848023772239685},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3455893397331238},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0742374062538147}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6845612525939941},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6456264853477478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6013288497924805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5379498600959778},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5183306932449341},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5172017812728882},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.43635135889053345},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4328545331954956},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.42848023772239685},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3455893397331238},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0742374062538147},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2022.3216980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3216980","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:36315551","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36315551","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:arXiv.org:2110.04792","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.04792","pdf_url":"https://arxiv.org/pdf/2110.04792","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.04792","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.04792","pdf_url":"https://arxiv.org/pdf/2110.04792","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2857486732","display_name":null,"funder_award_id":"2021YFF0500901","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6228099855","display_name":null,"funder_award_id":"61877056","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7302722026","display_name":null,"funder_award_id":"71991464","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W62794737","https://openalex.org/W1522301498","https://openalex.org/W1526868886","https://openalex.org/W1855641990","https://openalex.org/W1969868017","https://openalex.org/W2011792403","https://openalex.org/W2049981393","https://openalex.org/W2083624955","https://openalex.org/W2085261163","https://openalex.org/W2128019145","https://openalex.org/W2190691619","https://openalex.org/W2194775991","https://openalex.org/W2462831000","https://openalex.org/W2488101876","https://openalex.org/W2560535692","https://openalex.org/W2560609797","https://openalex.org/W2768879211","https://openalex.org/W2796347433","https://openalex.org/W2895439318","https://openalex.org/W2899663614","https://openalex.org/W2915414978","https://openalex.org/W2921849174","https://openalex.org/W2930967385","https://openalex.org/W2962888833","https://openalex.org/W2963150697","https://openalex.org/W2963177347","https://openalex.org/W2963188159","https://openalex.org/W2963403868","https://openalex.org/W2963756608","https://openalex.org/W2963892972","https://openalex.org/W2964056579","https://openalex.org/W2964249569","https://openalex.org/W2970971581","https://openalex.org/W2978088842","https://openalex.org/W2981378444","https://openalex.org/W2989915422","https://openalex.org/W2999391884","https://openalex.org/W3034597466","https://openalex.org/W3035355652","https://openalex.org/W3035398346","https://openalex.org/W3106250896","https://openalex.org/W3107372911","https://openalex.org/W3107992529","https://openalex.org/W3111535274","https://openalex.org/W3131500599","https://openalex.org/W3153465022","https://openalex.org/W3157938624","https://openalex.org/W3163945288","https://openalex.org/W3166470370","https://openalex.org/W3170544306","https://openalex.org/W3172345956","https://openalex.org/W3193686508","https://openalex.org/W3202459445","https://openalex.org/W3202538459","https://openalex.org/W3205586691","https://openalex.org/W3211490618","https://openalex.org/W4243493583","https://openalex.org/W4287124731","https://openalex.org/W4287273244","https://openalex.org/W4287273349","https://openalex.org/W4287324101","https://openalex.org/W4293584584","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W4394671432","https://openalex.org/W6631190155","https://openalex.org/W6687484953","https://openalex.org/W6739901393","https://openalex.org/W6755977528","https://openalex.org/W6766978945","https://openalex.org/W6785652829","https://openalex.org/W6797399245","https://openalex.org/W6840329539"],"related_works":["https://openalex.org/W4253893311","https://openalex.org/W2113785214","https://openalex.org/W2798721181","https://openalex.org/W3201205132","https://openalex.org/W4287600488","https://openalex.org/W4312694060","https://openalex.org/W4386075737","https://openalex.org/W4281696776","https://openalex.org/W4387967917","https://openalex.org/W4299867837"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"6D":[3,136],"vision":[4],"transformer":[5,65,87],"(6D-ViT),":[6],"a":[7,26,63,85,119],"transformer-based":[8],"instance":[9,38,104,135],"representation":[10],"learning":[11],"network":[12,123],"suitable":[13],"for":[14,112,170],"highly":[15],"accurate":[16],"category-level":[17],"object":[18],"pose":[19,137],"estimation":[20],"based":[21],"on":[22,84],"RGB-D":[23],"images.":[24],"Specifically,":[25],"novel":[27],"two-stream":[28],"encoder-decoder":[29],"framework":[30,51,166],"is":[31,138,174],"dedicated":[32],"to":[33,73,93],"exploring":[34],"complex":[35],"and":[36,45,59,89,109,128,150,159],"powerful":[37],"representations":[39,77,105],"from":[40,78,99,118],"RGB":[41,79],"images,":[42,80],"point":[43,100,148],"clouds,":[44],"categorical":[46],"shape":[47,125],"priors.":[48],"The":[49],"whole":[50],"consists":[52],"of":[53],"two":[54],"main":[55],"branches,":[56],"named":[57],"Pixelformer":[58,61],"Pointformer.":[60],"contains":[62],"pyramid":[64],"encoder":[66,88],"with":[67,124,157],"an":[68,90],"all-multilayer":[69],"perceptron":[70],"(MLP)":[71],"decoder":[72,92],"extract":[74],"pixelwise":[75],"appearance":[76,127],"while":[81],"Pointformer":[82],"relies":[83],"cascaded":[86],"all-MLP":[91],"acquire":[94],"the":[95,134,142,146,151,164],"pointwise":[96],"geometric":[97,129],"characteristics":[98],"clouds.":[101],"Then,":[102],"dense":[103],"(i.e.,":[106],"correspondence":[107],"matrix":[108],"deformation":[110],"field)":[111],"NOCS":[113,153],"model":[114],"reconstruction":[115],"are":[116],"obtained":[117],"multisource":[120],"aggregation":[121],"(MSA)":[122],"prior,":[126],"information":[130],"as":[131],"inputs.":[132],"Finally,":[133],"computed":[139],"by":[140],"solving":[141],"similarity":[143],"transformation":[144],"between":[145],"observed":[147],"clouds":[149],"reconstructed":[152],"representations.":[154],"Extensive":[155],"experiments":[156],"synthetic":[158],"real-world":[160],"datasets":[161],"demonstrate":[162],"that":[163],"proposed":[165],"achieves":[167],"state-of-the-art":[168],"performance":[169],"both":[171],"datasets.":[172],"Code":[173],"available":[175],"at":[176],"https://github.com/luzzou/6D-ViT.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":15}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}