{"id":"https://openalex.org/W4416748729","doi":"https://doi.org/10.1109/iros60139.2025.11246094","title":"Generalizable and Actionable Part Detection and Manipulation with SAM-rectified Segmentation and Iterative Pose Refinement","display_name":"Generalizable and Actionable Part Detection and Manipulation with SAM-rectified Segmentation and Iterative Pose Refinement","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748729","doi":"https://doi.org/10.1109/iros60139.2025.11246094"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018078638","display_name":"Sucheng Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sucheng Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425712","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0003-1317-0976"},"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/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003728286","display_name":"Yanyan Wei","orcid":"https://orcid.org/0000-0001-8818-6740"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Wei","raw_affiliation_strings":["Hefei University of Technology,Department of Computer Science and Information Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,Department of Computer Science and Information Engineering,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000011106","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0002-1755-8209"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu Liu","raw_affiliation_strings":["Hefei University of Technology,Department of Computer Science and Information Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,Department of Computer Science and Information Engineering,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010726528","display_name":"Cewu Lu","orcid":"https://orcid.org/0000-0002-4023-9257"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cewu Lu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19515","last_page":"19521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9557999968528748,"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":0.9557999968528748,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.006899999920278788,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.006200000178068876,"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/segmentation","display_name":"Segmentation","score":0.7544000148773193},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.621999979019165},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5698999762535095},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5256999731063843},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5130000114440918},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4943999946117401},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.492900013923645},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.4763999879360199},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4339999854564667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682999968528748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7570000290870667},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7544000148773193},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.621999979019165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5997999906539917},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5698999762535095},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5256999731063843},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.492900013923645},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35600000619888306},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.33550000190734863},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.26600000262260437},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":32,"referenced_works":["https://openalex.org/W2085261163","https://openalex.org/W2128019145","https://openalex.org/W2734349601","https://openalex.org/W2961368225","https://openalex.org/W2962759414","https://openalex.org/W2963177347","https://openalex.org/W2963351448","https://openalex.org/W2963892972","https://openalex.org/W3034949383","https://openalex.org/W3035131925","https://openalex.org/W3035398346","https://openalex.org/W3035624836","https://openalex.org/W3107992529","https://openalex.org/W3120441392","https://openalex.org/W3163945288","https://openalex.org/W3202459445","https://openalex.org/W3202538459","https://openalex.org/W4213019189","https://openalex.org/W4214773923","https://openalex.org/W4226321491","https://openalex.org/W4312274934","https://openalex.org/W4312803310","https://openalex.org/W4312818087","https://openalex.org/W4312877043","https://openalex.org/W4312893019","https://openalex.org/W4319300350","https://openalex.org/W4386065846","https://openalex.org/W4386072455","https://openalex.org/W4386075656","https://openalex.org/W4390190100","https://openalex.org/W4390874575","https://openalex.org/W4391216149"],"related_works":[],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,20,53,91,102,171,182],"perform":[3],"cross-category":[4,45],"object":[5,40,57],"perception":[6,46,141],"and":[7,26,33,38,73,80,157,191],"manipulation":[8,162,174],"is":[9,19,49],"highly":[10],"desirable":[11],"in":[12,100,164],"building":[13],"intelligent":[14],"robots.":[15],"One":[16],"promising":[17],"approach":[18],"define":[21],"the":[22,43,54,93,103,107,134,151],"concept":[23],"of":[24,47,106,136],"Generalizable":[25],"Actionable":[27],"Parts":[28],"(GAParts),":[29],"such":[30],"as":[31],"buttons":[32],"handles,":[34],"on":[35,120,143,154],"both":[36],"seen":[37],"unseen":[39],"categories.":[41],"However,":[42],"accurate":[44],"GAParts":[48],"still":[50],"challenging":[51],"due":[52],"large":[55],"inter-category":[56],"shape":[58],"variations.":[59],"To":[60],"address":[61],"this":[62],"issue,":[63],"we":[64,83,111,125],"introduce":[65,84],"SAMIR,":[66],"a":[67,85,116,183],"novel":[68],"framework":[69],"using":[70],"SAM-rectified":[71],"segmentation":[72,89,156],"Iterative":[74],"pose":[75,129,138,158],"Refinement":[76],"for":[77,186],"GAPart":[78,96,137],"detection":[79],"manipulation.":[81,188],"Firstly,":[82],"Segment":[86],"Anything":[87],"(SAM)":[88],"prior":[90],"rectify":[92],"unconfident,":[94],"fragmented":[95],"instance":[97,155],"proposals.":[98],"Secondly,":[99],"addition":[101],"zero-shot":[104],"generalization":[105],"SAM":[108],"foundation":[109],"model,":[110],"further":[112],"finetune":[113],"it":[114],"with":[115],"lightweight":[117],"adaptor":[118],"model":[119],"our":[121,180],"task":[122],"dataset.":[123],"Finally,":[124],"propose":[126],"an":[127,172],"iterative":[128],"refinement":[130],"procedure":[131],"that":[132,147,168],"improves":[133],"accuracy":[135],"estimation.":[139],"Our":[140,161,189],"experiments":[142,163],"GAPartNet":[144],"dataset":[145],"show":[146],"SAMIR":[148,169],"consistently":[149],"outperforms":[150],"baseline":[152],"method":[153,181],"estimation":[159],"tasks.":[160],"Sapien":[165],"simulator":[166],"illustrate":[167],"leads":[170],"improved":[173],"success":[175],"rate.":[176],"We":[177],"also":[178],"deploy":[179],"real":[184],"robot":[185],"real-world":[187],"code":[190],"video":[192],"are":[193],"available":[194],"at":[195],"sites.google.com/view/samir-gapart.":[196]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}