{"id":"https://openalex.org/W4402727700","doi":"https://doi.org/10.1109/cvpr52733.2024.00342","title":"ODIN: A Single Model for 2D and 3D Segmentation","display_name":"ODIN: A Single Model for 2D and 3D Segmentation","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402727700","doi":"https://doi.org/10.1109/cvpr52733.2024.00342"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.00342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5101550645","display_name":"Ayush Jain","orcid":"https://orcid.org/0000-0003-1411-2356"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayush Jain","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077243571","display_name":"Pushkal Katara","orcid":"https://orcid.org/0009-0007-4302-6955"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pushkal Katara","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028801762","display_name":"Nikolaos Gkanatsios","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolaos Gkanatsios","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019748928","display_name":"Adam W. Harley","orcid":"https://orcid.org/0000-0002-9851-4645"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam W. Harley","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035580849","display_name":"Gabriel Sarch","orcid":"https://orcid.org/0000-0002-4396-7612"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabriel Sarch","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036907475","display_name":"Kriti Aggarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kriti Aggarwal","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053028004","display_name":"Vishrav Chaudhary","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vishrav Chaudhary","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008661738","display_name":"Katerina Fragkiadaki","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katerina Fragkiadaki","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3564","last_page":"3574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/computer-science","display_name":"Computer science","score":0.6339181065559387},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5378479361534119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3482872247695923},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3385658264160156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6339181065559387},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5378479361534119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3482872247695923},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3385658264160156}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.00342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2586114507","https://openalex.org/W2594519801","https://openalex.org/W2963125977","https://openalex.org/W2964339842","https://openalex.org/W2965373594","https://openalex.org/W3010797203","https://openalex.org/W3034550906","https://openalex.org/W3034758614","https://openalex.org/W3034949383","https://openalex.org/W3110503160","https://openalex.org/W3138516171","https://openalex.org/W3168783492","https://openalex.org/W3172717135","https://openalex.org/W3203663566","https://openalex.org/W3204034406","https://openalex.org/W4214755140","https://openalex.org/W4214773923","https://openalex.org/W4226389400","https://openalex.org/W4282981845","https://openalex.org/W4286902310","https://openalex.org/W4293566037","https://openalex.org/W4306175953","https://openalex.org/W4307104049","https://openalex.org/W4312274934","https://openalex.org/W4312367717","https://openalex.org/W4312372834","https://openalex.org/W4312649925","https://openalex.org/W4312815172","https://openalex.org/W4312818263","https://openalex.org/W4312956471","https://openalex.org/W4313145913","https://openalex.org/W4313162371","https://openalex.org/W4366197620","https://openalex.org/W4372283849","https://openalex.org/W4377864307","https://openalex.org/W4382173244","https://openalex.org/W4383109105","https://openalex.org/W4385431115","https://openalex.org/W4386065742","https://openalex.org/W4386065833","https://openalex.org/W4386066076","https://openalex.org/W4386066126","https://openalex.org/W4386075729","https://openalex.org/W4386075819","https://openalex.org/W4386075898","https://openalex.org/W4388481600","https://openalex.org/W4389523655","https://openalex.org/W4390872744","https://openalex.org/W4390872957","https://openalex.org/W4390873582","https://openalex.org/W4390873929","https://openalex.org/W4390874575","https://openalex.org/W4399563599","https://openalex.org/W6733367512","https://openalex.org/W6747106673","https://openalex.org/W6791353385","https://openalex.org/W6796402304","https://openalex.org/W6802203484","https://openalex.org/W6802810016","https://openalex.org/W6840041517","https://openalex.org/W6841082114","https://openalex.org/W6846166657","https://openalex.org/W6851768568","https://openalex.org/W6853251676","https://openalex.org/W6854061876","https://openalex.org/W6859073004"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"State-of-the-art":[0],"models":[1],"on":[2,153,165,215],"contemporary":[3],"3D":[4,14,60,70,101,114,123,143,146,158,182,195,201],"segmentation":[5,160],"benchmarks":[6],"like":[7],"ScanNet":[8],"consume":[9,54],"and":[10,35,69,83,94,100,113,122,142,156,162,168,222],"label":[11,95],"dataset-":[12],"provided":[13],"point":[15,61,102,183,191],"clouds,":[16,103],"obtained":[17],"through":[18,126],"post":[19],"processing":[20],"of":[21,130,189],"sensed":[22,181],"multiview":[23,44],"RGB-D":[24],"images.":[25],"They":[26],"are":[27],"typically":[28],"trained":[29],"in-domain,":[30],"forego":[31],"large-scale":[32],"2D":[33,68,97,111,121,139],"pre-training":[34],"outperform":[36],"alternatives":[37],"that":[38,53,67,91,108],"featurize":[39],"the":[40,65,127,131,180,190,200,216,228],"posed":[41,55],"RGB-":[42],"D":[43],"images":[45,56,99],"instead.":[46],"The":[47],"gap":[48],"in":[49,187,204],"performance":[50,152,164],"between":[51,110],"methods":[52],"versus":[57],"post-":[58],"processed":[59],"clouds":[62],"has":[63],"fueled":[64],"belief":[66],"perception":[71,202],"require":[72],"distinct":[73],"model":[74,90,119],"architectures.":[75],"In":[76],"this":[77,81],"paper,":[78],"we":[79],"challenge":[80],"view":[82],"propose":[84],"ODIN":[85,149],"(Omni-Dimensional":[86],"INstance":[87],"segmentation),":[88],"a":[89,105,176,212],"can":[92,224],"segment":[93],"both":[96],"RGB":[98],"using":[104],"transformer":[106],"architecture":[107],"alternates":[109],"within-view":[112],"cross-view":[115],"information":[116],"fusion.":[117],"Our":[118,220],"differentiates":[120],"feature":[124,147],"oper-ations":[125],"positional":[128],"encodings":[129],"tokens":[132,141],"in-volved,":[133],"which":[134],"capture":[135],"pixel":[136],"coordinates":[137,144],"for":[138,145],"patch":[140],"tokens.":[148],"achieves":[150],"state-of-the-art":[151,214],"ScanNet200,":[154],"Matterport3D":[155],"AI2THOR":[157],"instance":[159],"benchmarks,":[161],"competitive":[163],"ScanNet,":[166],"S3DIS":[167],"COCO.":[169],"It":[170],"outperforms":[171],"all":[172],"previous":[173],"works":[174],"by":[175],"wide":[177],"margin":[178],"when":[179],"cloud":[184,192],"is":[185],"used":[186,198],"place":[188],"sampled":[193],"from":[194],"mesh.":[196],"When":[197],"as":[199],"engine":[203],"an":[205],"instructable":[206],"embodied":[207],"agent":[208],"architecture,":[209],"it":[210],"sets":[211],"new":[213],"TEACh":[217],"action-from-dialogue":[218],"benchmark.":[219],"code":[221],"checkpoints":[223],"be":[225],"found":[226],"at":[227],"project":[229],"website":[230]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}