{"id":"https://openalex.org/W4383109105","doi":"https://doi.org/10.1109/icra48891.2023.10160590","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","display_name":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383109105","doi":"https://doi.org/10.1109/icra48891.2023.10160590"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5075529365","display_name":"Jonas Schult","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Schult","raw_affiliation_strings":["RWTH Aachen University,Computer Vision Group,Germany","Computer Vision Group, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Computer Vision Group,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Computer Vision Group, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073714926","display_name":"Francis Engelmann","orcid":"https://orcid.org/0000-0001-5745-2137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francis Engelmann","raw_affiliation_strings":["ETH Zürich,Computer Vision and Learning Group,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich,Computer Vision and Learning Group,Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071563379","display_name":"Alexander Hermans","orcid":"https://orcid.org/0000-0003-2127-0782"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Hermans","raw_affiliation_strings":["RWTH Aachen University,Computer Vision Group,Germany","Computer Vision Group, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Computer Vision Group,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Computer Vision Group, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006347979","display_name":"Or Litany","orcid":"https://orcid.org/0000-0001-6700-7379"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Or Litany","raw_affiliation_strings":["NVIDIA,Santa Clara,USA","NVIDIA, Santa Clara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056265728","display_name":"Siyu Tang","orcid":"https://orcid.org/0000-0002-1015-4770"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyu Tang","raw_affiliation_strings":["ETH Zürich,Computer Vision and Learning Group,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich,Computer Vision and Learning Group,Switzerland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071006649","display_name":"Bastian Leibe","orcid":"https://orcid.org/0000-0003-4225-0051"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bastian Leibe","raw_affiliation_strings":["RWTH Aachen University,Computer Vision Group,Germany","Computer Vision Group, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Computer Vision Group,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Computer Vision Group, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":76.177,"has_fulltext":false,"cited_by_count":205,"citation_normalized_percentile":{"value":0.99949787,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8216","last_page":"8223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.7481433749198914},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7189096212387085},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.664641261100769},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6006683707237244},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5699178576469421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5652446150779724},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.5385552048683167},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5067198872566223},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3637263774871826},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3391275107860565}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7481433749198914},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7189096212387085},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.664641261100769},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6006683707237244},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5699178576469421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5652446150779724},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.5385552048683167},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5067198872566223},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3637263774871826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3391275107860565},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W607748843","https://openalex.org/W639708223","https://openalex.org/W1901129140","https://openalex.org/W1920022804","https://openalex.org/W1995444699","https://openalex.org/W1999478155","https://openalex.org/W2095705004","https://openalex.org/W2194775991","https://openalex.org/W2211722331","https://openalex.org/W2222512263","https://openalex.org/W2339077268","https://openalex.org/W2460657278","https://openalex.org/W2560609797","https://openalex.org/W2594519801","https://openalex.org/W2624273542","https://openalex.org/W2624503621","https://openalex.org/W2737234477","https://openalex.org/W2769312834","https://openalex.org/W2883254424","https://openalex.org/W2904332125","https://openalex.org/W2914371536","https://openalex.org/W2928059219","https://openalex.org/W2939384298","https://openalex.org/W2948410735","https://openalex.org/W2959771705","https://openalex.org/W2962759414","https://openalex.org/W2963121255","https://openalex.org/W2963125977","https://openalex.org/W2963150697","https://openalex.org/W2963182550","https://openalex.org/W2963587345","https://openalex.org/W2990613095","https://openalex.org/W2995182785","https://openalex.org/W3034430142","https://openalex.org/W3034550906","https://openalex.org/W3034949383","https://openalex.org/W3036843665","https://openalex.org/W3096609285","https://openalex.org/W3104141662","https://openalex.org/W3106546328","https://openalex.org/W3138516171","https://openalex.org/W3166470370","https://openalex.org/W3166573884","https://openalex.org/W3172351327","https://openalex.org/W3204034406","https://openalex.org/W3213165621","https://openalex.org/W3215207332","https://openalex.org/W4206398307","https://openalex.org/W4214526701","https://openalex.org/W4214624153","https://openalex.org/W4214755140","https://openalex.org/W4214773923","https://openalex.org/W4221154304","https://openalex.org/W4221163288","https://openalex.org/W4241307704","https://openalex.org/W4246999471","https://openalex.org/W4312274934","https://openalex.org/W4312616477","https://openalex.org/W4312649925","https://openalex.org/W4312815172","https://openalex.org/W4312903773","https://openalex.org/W4313145913","https://openalex.org/W4385245566","https://openalex.org/W6637131181","https://openalex.org/W6674330103","https://openalex.org/W6679855945","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6763229141","https://openalex.org/W6780179280","https://openalex.org/W6784333009","https://openalex.org/W6798837711"],"related_works":["https://openalex.org/W4389574804","https://openalex.org/W3016928466","https://openalex.org/W2936725271","https://openalex.org/W3150655618","https://openalex.org/W3108295644","https://openalex.org/W4287694812","https://openalex.org/W3128716822","https://openalex.org/W3046762217","https://openalex.org/W4399442168","https://openalex.org/W2114282491"],"abstract_inverted_index":{"Modern":[0],"3D":[1,40,60],"semantic":[2,41],"instance":[3,42,57,72,77,83,102,107,153],"segmentation":[4],"approaches":[5],"predominantly":[6],"rely":[7],"on":[8,20,123,160],"specialized":[9],"voting":[10,125],"mechanisms":[11,139],"followed":[12],"by":[13,87],"carefully":[14],"designed":[15],"geometric":[16,130,137],"clustering":[17],"techniques.":[18],"Building":[19],"the":[21,35,82,101],"successes":[22],"of":[23],"recent":[24],"Transformer-based":[25,37],"methods":[26],"for":[27,39],"object":[28,71],"detection":[29],"and":[30,145,171],"image":[31],"segmentation,":[32],"we":[33,47],"propose":[34],"first":[36],"approach":[38],"segmentation.":[43],"We":[44],"show":[45],"that":[46,150],"can":[48],"leverage":[49],"generic":[50],"Transformer":[51,80],"building":[52],"blocks":[53],"to":[54,90],"directly":[55,104,151],"predict":[56],"masks":[58,108],"from":[59],"point":[61,91,99],"clouds.":[62],"In":[63],"our":[64],"model":[65],"-":[66,69],"called":[67],"Mask3D":[68,111,155],"each":[70],"is":[73],"represented":[74],"as":[75,133],"an":[76],"query.":[78],"Using":[79],"decoders,":[81],"queries":[84,103],"are":[85],"learned":[86],"iteratively":[88],"attending":[89],"cloud":[92],"features":[93],"at":[94],"multiple":[95],"scales.":[96],"Combined":[97],"with":[98],"features,":[100],"yield":[105],"all":[106],"in":[109],"parallel.":[110],"has":[112],"several":[113],"advantages":[114],"over":[115],"current":[116],"state-of-the-art":[117,159],"approaches,":[118],"since":[119],"it":[120],"neither":[121],"relies":[122],"(1)":[124],"schemes":[126],"which":[127],"require":[128],"hand-selected":[129],"properties":[131],"(such":[132],"centers)":[134],"nor":[135],"(2)":[136],"grouping":[138],"requiring":[140],"manually-tuned":[141],"hyper-parameters":[142],"(e.g.":[143],"radii)":[144],"(3)":[146],"enables":[147],"a":[148,157],"loss":[149],"optimizes":[152],"masks.":[154],"sets":[156],"new":[158],"ScanNet":[161],"test":[162,173],"(+6.2mAP),":[163],"S3DIS":[164],"6-fold":[165],"(+10.1":[166],"mAP),":[167],"STPLS3D":[168],"(+11.2":[169],"mAP)":[170],"ScanNet200":[172],"(+12.4":[174],"mAP).":[175]},"counts_by_year":[{"year":2026,"cited_by_count":36},{"year":2025,"cited_by_count":80},{"year":2024,"cited_by_count":75},{"year":2023,"cited_by_count":14}],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2025-10-10T00:00:00"}