{"id":"https://openalex.org/W4413925642","doi":"https://doi.org/10.1109/icra55743.2025.11127530","title":"Multi-Layer Feature Exchange Transformer for Multi-View 6D Object Pose Estimation in Robot Bin Picking","display_name":"Multi-Layer Feature Exchange Transformer for Multi-View 6D Object Pose Estimation in Robot Bin Picking","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925642","doi":"https://doi.org/10.1109/icra55743.2025.11127530"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":null,"display_name":"Momen Khalil","orcid":null},"institutions":[{"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"],"is_corresponding":true,"raw_author_name":"Momen Khalil","raw_affiliation_strings":["Technical University of Munich,Department of Informatics,Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Department of Informatics,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007330724","display_name":"Vincent Dietrich","orcid":"https://orcid.org/0000-0003-0568-9727"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vincent Dietrich","raw_affiliation_strings":["Siemens AG, Munich,Germany"],"affiliations":[{"raw_affiliation_string":"Siemens AG, Munich,Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045382199","display_name":"Slobodan Ili\u0107","orcid":"https://orcid.org/0000-0002-3413-1936"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Slobodan Ilic","raw_affiliation_strings":["Technical University of Munich,Department of Informatics,Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Department of Informatics,Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27132869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12415","last_page":"12421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9868000149726868,"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":0.9868000149726868,"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/T13382","display_name":"Robotics and Automated Systems","score":0.958899974822998,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9448000192642212,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6886598467826843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6613165140151978},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6332521438598633},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.60554438829422},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5509034991264343},{"id":"https://openalex.org/keywords/bin","display_name":"Bin","score":0.519693911075592},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.506921112537384},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4390820562839508},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42524459958076477},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42097383737564087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3465002775192261},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13818827271461487},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09568876028060913},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06606170535087585},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.05516248941421509}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6886598467826843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6613165140151978},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6332521438598633},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.60554438829422},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5509034991264343},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.519693911075592},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.506921112537384},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4390820562839508},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42524459958076477},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42097383737564087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3465002775192261},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13818827271461487},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09568876028060913},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06606170535087585},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.05516248941421509},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":29,"referenced_works":["https://openalex.org/W1526868886","https://openalex.org/W1901129140","https://openalex.org/W2049981393","https://openalex.org/W2085261163","https://openalex.org/W2604236302","https://openalex.org/W2963150697","https://openalex.org/W2963177347","https://openalex.org/W2963756608","https://openalex.org/W2989915422","https://openalex.org/W3009516594","https://openalex.org/W3034268164","https://openalex.org/W3034275286","https://openalex.org/W3034986117","https://openalex.org/W3092774272","https://openalex.org/W3133860213","https://openalex.org/W3143558489","https://openalex.org/W3160889789","https://openalex.org/W3179923621","https://openalex.org/W3204319309","https://openalex.org/W4247726808","https://openalex.org/W4312253793","https://openalex.org/W4312843170","https://openalex.org/W4321377343","https://openalex.org/W4383108286","https://openalex.org/W4383108328","https://openalex.org/W4383108938","https://openalex.org/W4383503782","https://openalex.org/W4385245566","https://openalex.org/W4391974623"],"related_works":["https://openalex.org/W2107701374","https://openalex.org/W1616588898","https://openalex.org/W4395000504","https://openalex.org/W4249504934","https://openalex.org/W2183416055","https://openalex.org/W2568867011","https://openalex.org/W1994114538","https://openalex.org/W2413205705","https://openalex.org/W2735644334","https://openalex.org/W138879321"],"abstract_inverted_index":{"Accurate":[0],"6D":[1,80],"object":[2],"pose":[3,27,81,142,172],"estimation":[4,28,82,143,173],"is":[5],"crucial":[6],"in":[7,11,23,141,148],"industrial":[8],"automation,":[9],"particularly":[10],"robotic":[12],"bin":[13],"picking,":[14],"where":[15],"objects":[16],"are":[17],"often":[18,56],"textureless,":[19],"reflective,":[20],"and":[21,44,48,98,145,168],"arranged":[22],"cluttered":[24],"environments.":[25],"Multi-view":[26],"methods":[29,35,55],"offer":[30],"significant":[31,139],"advantages":[32],"over":[33],"single-view":[34],"by":[36,83],"providing":[37],"more":[38],"comprehensive":[39],"information,":[40,136],"effectively":[41],"handling":[42],"occlusions":[43],"lack":[45],"of":[46,129,134],"features,":[47],"resolving":[49],"depth":[50],"ambiguities.":[51],"However,":[52],"current":[53],"multi-view":[54,69,135,171],"rely":[57],"on":[58,127,156],"late-stage":[59],"information":[60],"fusion,":[61],"limiting":[62],"their":[63],"ability":[64],"to":[65,77,102,138],"fully":[66],"exploit":[67],"complementary":[68],"data.":[70],"This":[71,94],"paper":[72],"presents":[73],"a":[74,85,112],"novel":[75],"approach":[76,95,155],"enhance":[78],"multiview":[79],"introducing":[84],"Feature":[86],"Exchange":[87],"Transformer":[88],"(FET)":[89],"for":[90,115],"early-stage":[91],"feature":[92,105,118],"fusion.":[93],"leverages":[96],"self-attention":[97],"epipolar":[99],"cross-attention":[100],"mechanisms":[101],"enable":[103],"multi-layer":[104],"aggregation":[106],"across":[107],"views.":[108],"Additionally,":[109],"we":[110],"introduce":[111],"coarse-to-fine":[113],"strategy":[114],"an":[116],"efficient":[117],"exchange":[119],"at":[120],"multiple":[121],"network":[122],"layers.":[123],"Our":[124],"method,":[125],"implemented":[126],"top":[128],"EpiSurfEmb[1],":[130],"enhances":[131],"the":[132,157,165],"utilization":[133],"leading":[137],"improvements":[140],"accuracy":[144],"robustness,":[146],"especially":[147],"challenging":[149],"bin-picking":[150],"scenarios.":[151],"We":[152],"evaluate":[153],"our":[154],"ROBI":[158],"dataset,":[159],"demonstrating":[160],"that":[161],"it":[162],"outperforms":[163],"both":[164],"baseline":[166],"EpiSurfEmb":[167],"other":[169],"state-of-the-art":[170],"methods.":[174]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}