{"id":"https://openalex.org/W4413146483","doi":"https://doi.org/10.1109/cvpr52734.2025.01087","title":"CRISP: Object Pose and Shape Estimation with Test-Time Adaptation","display_name":"CRISP: Object Pose and Shape Estimation with Test-Time Adaptation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413146483","doi":"https://doi.org/10.1109/cvpr52734.2025.01087"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":"https://openalex.org/A5006694174","display_name":"Jingnan Shi","orcid":"https://orcid.org/0000-0001-6918-3237"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingnan Shi","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information &#x0026; Decision Systems (LIDS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information &#x0026; Decision Systems (LIDS)","institution_ids":["https://openalex.org/I4210143601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047680302","display_name":"Rajat Talak","orcid":"https://orcid.org/0000-0002-6132-395X"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajat Talak","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information &#x0026; Decision Systems (LIDS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information &#x0026; Decision Systems (LIDS)","institution_ids":["https://openalex.org/I4210143601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103226976","display_name":"Harry Zhang","orcid":"https://orcid.org/0009-0003-1903-274X"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harry Zhang","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information &#x0026; Decision Systems (LIDS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information &#x0026; Decision Systems (LIDS)","institution_ids":["https://openalex.org/I4210143601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103840309","display_name":"David Jin","orcid":"https://orcid.org/0000-0002-1516-8629"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Jin","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information &#x0026; Decision Systems (LIDS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information &#x0026; Decision Systems (LIDS)","institution_ids":["https://openalex.org/I4210143601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042157108","display_name":"Luca Carlone","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luca Carlone","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information &#x0026; Decision Systems (LIDS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information &#x0026; Decision Systems (LIDS)","institution_ids":["https://openalex.org/I4210143601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8048,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91298167,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11644","last_page":"11653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9927999973297119,"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"}},"topics":[{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9927999973297119,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.984000027179718,"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":0.98089998960495,"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/computer-science","display_name":"Computer science","score":0.6913406848907471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6423763632774353},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6260306239128113},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6224898099899292},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5616506338119507},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48765337467193604},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4265247583389282},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32075750827789307},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.05828666687011719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6913406848907471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6423763632774353},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6260306239128113},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6224898099899292},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5616506338119507},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48765337467193604},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4265247583389282},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32075750827789307},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.05828666687011719},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W2997567050","https://openalex.org/W4387967917","https://openalex.org/W4387968151","https://openalex.org/W4386925306","https://openalex.org/W3132124459","https://openalex.org/W2946083937","https://openalex.org/W3101088080","https://openalex.org/W2894986065"],"abstract_inverted_index":{"We":[0,166],"consider":[1],"the":[2,80,87,95,108,152,170,184,219],"problem":[3,111],"of":[4,90,140,191,213],"estimating":[5,50],"object":[6,23],"pose":[7,24,54,64],"and":[8,25,45,65,103,160,175,211],"shape":[9,26,36,43,66,81,96,101,109],"from":[10],"an":[11,32,62,99,125,201],"RGB-D":[12],"image.":[13],"Our":[14],"first":[15],"contribution":[16],"is":[17,83,144,189],"to":[18,112,135,154,163,203,205],"introduce":[19,131],"CRISP,":[20],"a":[21,46,57,75,113,132,147,193],"category-agnostic":[22],"estimation":[27,71],"pipeline.":[28],"The":[29,142],"pipeline":[30,134],"implements":[31],"encoder-decoder":[33],"model":[34],"for":[35,41,49,53],"estimation.":[37,55],"It":[38],"uses":[39,161],"FiLM-conditioning":[40],"implicit":[42],"reconstruction":[44],"DPT-based":[47],"network":[48],"pose-normalized":[51],"points":[52],"As":[56],"second":[58],"contribution,":[59],"we":[60,93,130],"propose":[61],"optimization-based":[63],"corrector":[67,153],"that":[68,79,105],"can":[69,120],"correct":[70],"errors":[72],"caused":[73],"by":[74,124],"domain":[76,138,195],"gap.":[77,196],"Observing":[78],"decoder":[82,97],"well":[84],"behaved":[85],"in":[86],"convex":[88],"hull":[89],"known":[91],"shapes,":[92],"approximate":[94],"with":[98],"active":[100],"model,":[102],"show":[104],"this":[106],"reduces":[107],"correction":[110],"constrained":[114],"linear":[115],"least":[116],"squares":[117],"problem,":[118],"which":[119,150],"be":[121],"solved":[122],"efficiently":[123],"interior":[126],"point":[127],"algorithm.":[128],"Third,":[129],"self-training":[133,143,188],"perform":[136],"self-supervised":[137],"adaptation":[139],"CRISP.":[141,165],"based":[145],"on":[146,172,182,218],"correct-and-certify":[148],"approach,":[149],"leverages":[151],"generate":[155],"pseudo-labels":[156],"at":[157],"test":[158],"time,":[159],"them":[162],"self-train":[164],"demonstrate":[167],"CRISP":[168,178,198],"(and":[169],"self-training)":[171],"YCBV,":[173],"SPE3R,":[174],"NOCS":[176],"datasets.":[177,185],"shows":[179,200],"high":[180],"performance":[181],"all":[183],"Moreover,":[186],"our":[187],"capable":[190],"bridging":[192],"large":[194],"Finally,":[197],"also":[199],"ability":[202],"generalize":[204],"unseen":[206],"objects.":[207],"Code,":[208],"pre-trained":[209],"models":[210],"videos":[212],"sample":[214],"results":[215],"are":[216],"available":[217],"project":[220],"webpage.":[221],"<sup":[222],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[223],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[224]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}