{"id":"https://openalex.org/W7105837102","doi":"https://doi.org/10.1109/tcsvt.2025.3633750","title":"Language-Assisted Reconstruction for Self-Supervised Category-Level 6D Object Pose Estimation With Coarse-to-Fine Correspondence Optimization","display_name":"Language-Assisted Reconstruction for Self-Supervised Category-Level 6D Object Pose Estimation With Coarse-to-Fine Correspondence Optimization","publication_year":2025,"publication_date":"2025-11-17","ids":{"openalex":"https://openalex.org/W7105837102","doi":"https://doi.org/10.1109/tcsvt.2025.3633750"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3633750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3633750","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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":null,"display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"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":"Jun Yu","raw_affiliation_strings":["Department of Orthopedics, First Affiliated Hospital, the Division of Life Sciences and Medicine, the Department of Automation, Institute of Advanced Technology, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3197-8103","affiliations":[{"raw_affiliation_string":"Department of Orthopedics, First Affiliated Hospital, the Division of Life Sciences and Medicine, the Department of Automation, Institute of Advanced Technology, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yunxiang Zhang","orcid":"https://orcid.org/0009-0003-1980-7859"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunxiang Zhang","raw_affiliation_strings":["Department of Automation, USTC, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-1980-7859","affiliations":[{"raw_affiliation_string":"Department of Automation, USTC, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zerui Zhang","orcid":"https://orcid.org/0009-0002-1976-0889"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zerui Zhang","raw_affiliation_strings":["Department of Automation, USTC, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-1976-0889","affiliations":[{"raw_affiliation_string":"Department of Automation, USTC, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Xu","orcid":"https://orcid.org/0009-0005-4118-3936"},"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"]},{"id":"https://openalex.org/I4210165047","display_name":"Hefei First People's Hospital","ror":"https://ror.org/05qwgjd68","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210165047"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["First Affiliated Hospital, Division of Life Sciences and Medicine, USTC, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-4118-3936","affiliations":[{"raw_affiliation_string":"First Affiliated Hospital, Division of Life Sciences and Medicine, USTC, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210165047"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaolong Shi","orcid":"https://orcid.org/0000-0002-2337-9055"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Shi","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2337-9055","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49572898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"4","first_page":"4693","last_page":"4706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5289000272750854,"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":0.5289000272750854,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.2660999894142151,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.04910000041127205,"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/ambiguity","display_name":"Ambiguity","score":0.649399995803833},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6456000208854675},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5867000222206116},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5784000158309937},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5044999718666077},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5034999847412109},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47749999165534973},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44999998807907104},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.3610000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7671999931335449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7278000116348267},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.649399995803833},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6456000208854675},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6448000073432922},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5867000222206116},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5784000158309937},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47749999165534973},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.3610000014305115},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C3004257","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Correspondence problem","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3633750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3633750","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G450612882","display_name":null,"funder_award_id":"62276242","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8280234501","display_name":null,"funder_award_id":"2023-ZM01Z001","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"category-level":[1],"6D":[2],"pose":[3],"estimation":[4],"has":[5],"emerged":[6],"as":[7],"a":[8,61,74,79,87,122],"task":[9],"of":[10,16,33],"paramount":[11],"significance":[12],"within":[13,56,204],"the":[14,31,52,94,103,112,158,167,184,205],"field":[15],"computer":[17],"vision.":[18],"Despite":[19],"recent":[20],"advancements,":[21],"current":[22],"self-supervised":[23,194,206],"methods":[24,198],"grapple":[25],"with":[26],"two":[27],"critical":[28],"challenges.":[29],"Primarily,":[30],"ability":[32],"existing":[34,197],"networks":[35],"to":[36,64,101,128,143,170,174],"accurately":[37],"reconstruct":[38],"object":[39,119],"models":[40],"is":[41,126],"constrained":[42],"by":[43,132],"pronounced":[44],"part-level":[45],"shape":[46,135],"variations":[47],"across":[48],"specific":[49],"categories.":[50],"Additionally,":[51,121],"persistent":[53],"many-to-one":[54,168],"ambiguity":[55,169],"pixel-to-point":[57],"cloud":[58],"correspondences":[59],"poses":[60],"significant":[62],"barrier":[63],"achieving":[65],"robust":[66],"performance.":[67],"To":[68],"address":[69],"these":[70],"challenges,":[71],"we":[72],"propose":[73],"novel":[75],"approach":[76,195],"that":[77,192],"includes":[78],"Language-Assisted":[80],"Memory-Encoding":[81],"Shape":[82],"Reconstruction":[83],"(LMR)":[84],"module":[85,139],"and":[86,107,117,151,186,199],"Coarse-to-Fine":[88],"Correspondence":[89],"Optimization":[90],"(CFCO)":[91],"module.":[92],"In":[93],"LMR":[95],"module,":[96],"language":[97],"descriptions":[98],"are":[99],"leveraged":[100],"bridge":[102],"gap":[104],"between":[105,114],"virtual":[106],"real":[108],"images,":[109],"thereby":[110],"improving":[111],"alignment":[113],"learned":[115],"representations":[116],"real-world":[118],"appearances.":[120],"memory":[123],"encoding":[124],"mechanism":[125],"introduced":[127],"enhance":[129],"reconstruction":[130],"accuracy":[131],"capturing":[133],"fine-grained":[134],"variations.":[136],"The":[137],"CFCO":[138],"utilizes":[140],"Hungarian":[141],"matching":[142],"generate":[144],"one-to-one":[145],"pseudo":[146],"labels":[147],"at":[148],"both":[149],"region":[150],"pixel":[152],"levels,":[153],"providing":[154],"explicit":[155],"supervision":[156],"for":[157],"corresponding":[159],"similarity":[160],"matrices.":[161],"Furthermore,":[162],"this":[163],"process":[164],"helps":[165],"alleviate":[166],"some":[171],"extent,":[172],"leading":[173],"more":[175],"accurate":[176],"correspondence":[177],"learning.":[178],"We":[179],"evaluate":[180],"our":[181,193],"method":[182],"on":[183],"REAL275":[185],"WILD6D":[187],"datasets.":[188],"Extensive":[189],"experiments":[190],"demonstrate":[191],"outperforms":[196],"achieves":[200],"new":[201],"state-of-the-art":[202],"results":[203],"framework.":[207]},"counts_by_year":[],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2025-11-17T00:00:00"}