{"id":"https://openalex.org/W7123356066","doi":"https://doi.org/10.1109/lra.2026.3652073","title":"VERM: Leveraging Foundation Models to Create a <u>V</u> irtual <u>E</u> ye for Efficient 3D <u>R</u> obotic <u>M</u> anipulation","display_name":"VERM: Leveraging Foundation Models to Create a <u>V</u> irtual <u>E</u> ye for Efficient 3D <u>R</u> obotic <u>M</u> anipulation","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123356066","doi":"https://doi.org/10.1109/lra.2026.3652073"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3652073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3652073","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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":null,"display_name":"Yixiang Chen","orcid":"https://orcid.org/0009-0000-2895-9203"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixiang Chen","raw_affiliation_strings":["New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2895-9203","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122852776","display_name":"Yan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8239-7229","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122905422","display_name":"Keji He","orcid":null},"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":"Keji He","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-5136-8444","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867545","display_name":"Peiyan Li","orcid":"https://orcid.org/0009-0005-8404-5779"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiyan Li","raw_affiliation_strings":["New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-8404-5779","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122853687","display_name":"Liang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5224-8647","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"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":0.05000338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"3","first_page":"2482","last_page":"2489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.73089998960495,"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":0.73089998960495,"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":0.08129999786615372,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.035100001841783524,"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/speedup","display_name":"Speedup","score":0.8611999750137329},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5641000270843506},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5090000033378601},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5080000162124634},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3781000077724457},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3758000135421753},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3747999966144562}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8611999750137329},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7350999712944031},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5641000270843506},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5090000033378601},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4546999931335449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4000999927520752},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2879999876022339},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3652073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3652073","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1383591865","display_name":null,"funder_award_id":"62276261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5156147101","display_name":null,"funder_award_id":"62236010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8053739178","display_name":null,"funder_award_id":"62322607","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8601551012","display_name":null,"funder_award_id":"ZR2025QC1566","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1971086298","https://openalex.org/W2082511574","https://openalex.org/W2147299944","https://openalex.org/W3007769740","https://openalex.org/W3174849255","https://openalex.org/W4313026212","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4385245566","https://openalex.org/W4385430679","https://openalex.org/W4390874575","https://openalex.org/W4394828156","https://openalex.org/W4402354045","https://openalex.org/W4402354046","https://openalex.org/W4402354093","https://openalex.org/W4402890475","https://openalex.org/W4403277141","https://openalex.org/W4404612908","https://openalex.org/W4405785541","https://openalex.org/W4408757728","https://openalex.org/W4414050902"],"related_works":[],"abstract_inverted_index":{"When":[0],"performing":[1],"3D":[2,89,102],"manipulation":[3],"tasks,":[4],"robots":[5],"have":[6],"to":[7,35,80],"execute":[8],"action":[9,103],"planning":[10,104],"based":[11],"on":[12,122,162],"perceptions":[13],"from":[14,86],"multiple":[15],"fixed":[16],"cameras.":[17],"The":[18],"multi-camera":[19],"setup":[20],"introduces":[21],"substantial":[22],"redundancy":[23],"and":[24,31,49,97,105,114,127,149],"irrelevant":[25],"information,":[26],"which":[27,92],"increases":[28],"computational":[29],"costs":[30],"forces":[32],"the":[33,56,75,87,131],"model":[34],"spend":[36],"extra":[37],"training":[38,147],"time":[39,148],"extracting":[40],"crucial":[41],"task-relevant":[42,52],"details.":[43],"To":[44,100],"filter":[45],"out":[46],"redundant":[47],"information":[48,96],"accurately":[50],"extract":[51],"features,":[53],"we":[54,108],"propose":[55],"<bold":[57,63,67,70,142,150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[58,61,64,68,71,143,151,167],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">VERM</b>":[59],"(<bold":[60],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">V</b>irtual":[62],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">E</b>ye":[65],"for":[66],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</b>obotic":[69],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</b>anipulation)":[72],"method,":[73,135],"leveraging":[74],"knowledge":[76],"in":[77,146,154],"foundation":[78],"models":[79],"imagine":[81],"a":[82,111,115],"virtual":[83],"task-adaptive":[84],"view":[85],"constructed":[88],"point":[90],"cloud,":[91],"efficiently":[93],"captures":[94],"necessary":[95],"mitigates":[98],"occlusion.":[99],"facilitate":[101],"fine-grained":[106],"manipulation,":[107],"further":[109],"design":[110],"depth-aware":[112],"module":[113],"dynamic":[116],"coarse-to-fine":[117],"procedure.":[118],"Extensive":[119],"experimental":[120],"results":[121,158],"both":[123],"simulation":[124],"benchmark":[125],"RLBench":[126],"real-world":[128],"evaluations":[129],"demonstrate":[130],"effectiveness":[132],"of":[133],"our":[134,163],"surpassing":[136],"previous":[137],"state-of-the-art":[138],"methods":[139],"while":[140],"achieving":[141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1.89\u00d7</b>":[144],"speedup":[145,153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1.54\u00d7</b>":[152],"inference":[155],"speed.":[156],"More":[157],"can":[159],"be":[160],"found":[161],"project":[164],"website:":[165],"<uri":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://verm-ral.github.io/</uri>.":[168]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-01-14T00:00:00"}