{"id":"https://openalex.org/W4405030397","doi":"https://doi.org/10.48550/arxiv.2411.19458","title":"Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning","display_name":"Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning","publication_year":2024,"publication_date":"2024-11-29","ids":{"openalex":"https://openalex.org/W4405030397","doi":"https://doi.org/10.48550/arxiv.2411.19458"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.19458","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.19458","pdf_url":"https://arxiv.org/pdf/2411.19458","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.19458","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100658703","display_name":"Yang You","orcid":"https://orcid.org/0000-0003-0125-0792","observed_orcids":["https://orcid.org/0000-0003-0125-0792"]},"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":"You, Yang","raw_affiliation_strings":["Department of Computer Science , Stanford University , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Stanford University , U.S.A","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071196017","display_name":"Yixin Li","orcid":"https://orcid.org/0009-0006-8274-1954","observed_orcids":["https://orcid.org/0009-0006-8274-1954"]},"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":"Li, Yixin","raw_affiliation_strings":["Department of Computer Science , Stanford University , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Stanford University , U.S.A","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050560702","display_name":"Congyue Deng","orcid":"https://orcid.org/0000-0002-0177-218X","observed_orcids":["https://orcid.org/0000-0002-0177-218X"]},"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":"Deng, Congyue","raw_affiliation_strings":["Department of Computer Science , Stanford University , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Stanford University , U.S.A","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372090","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0147-5166","observed_orcids":["https://orcid.org/0000-0003-0147-5166"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Yue","raw_affiliation_strings":["Department of Computer Science , University of Southern California , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Southern California , U.S.A","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111954013","display_name":"Leonidas J. Guibas","orcid":"https://orcid.org/0000-0002-8315-4886","observed_orcids":["https://orcid.org/0000-0002-8315-4886"]},"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":"Guibas, Leonidas","raw_affiliation_strings":["Department of Computer Science , Stanford University , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Stanford University , U.S.A","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.448199987411499,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.448199987411499,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.2517000138759613,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.14000000059604645,"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/vision-transformer","display_name":"vision transformer","score":0.5600000023841858},{"id":"https://openalex.org/keywords/vit","display_name":"ViT","score":0.734000027179718},{"id":"https://openalex.org/keywords/viewpoint-consistency","display_name":"viewpoint consistency","score":0.5759999752044678},{"id":"https://openalex.org/keywords/semantic-embeddings","display_name":"semantic embeddings","score":0.6340000033378601},{"id":"https://openalex.org/keywords/pose-estimation","display_name":"pose estimation","score":0.8849999904632568},{"id":"https://openalex.org/keywords/object-tracking","display_name":"object tracking","score":0.8799999952316284},{"id":"https://openalex.org/keywords/semantic-transfer","display_name":"semantic transfer","score":0.9430000185966492}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6217513084411621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49923086166381836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42893779277801514},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.19458","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.19458","pdf_url":"https://arxiv.org/pdf/2411.19458","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.19458","doi":"https://doi.org/10.48550/arxiv.2411.19458","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.19458","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.19458","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.19458","pdf_url":"https://arxiv.org/pdf/2411.19458","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108"},{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405030397.pdf","grobid_xml":"https://content.openalex.org/works/W4405030397.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2963188159","https://openalex.org/W2963557767","https://openalex.org/W3094502228","https://openalex.org/W4226369981","https://openalex.org/W4311640782","https://openalex.org/W4366208220","https://openalex.org/W4387225729","https://openalex.org/W4387964188","https://openalex.org/W4389217158","https://openalex.org/W4403562352","https://openalex.org/W4403842181","https://openalex.org/W4403842231","https://openalex.org/W4403906568","https://openalex.org/W4404612623","https://openalex.org/W4404725027","https://openalex.org/W4415796124","https://openalex.org/W4415798784","https://openalex.org/W7133198812","https://openalex.org/W7133241772","https://openalex.org/W7133244048"],"related_works":["https://openalex.org/W4403562352","https://openalex.org/W7116123138","https://openalex.org/W7162761896","https://openalex.org/W7212225127","https://openalex.org/W7128052114","https://openalex.org/W7115571925","https://openalex.org/W4402754274","https://openalex.org/W7163069032","https://openalex.org/W7220885473","https://openalex.org/W4386978457"],"abstract_inverted_index":{"Vision":[0],"foundation":[1],"models,":[2],"particularly":[3],"the":[4,40,60,109],"ViT":[5],"family,":[6],"have":[7],"revolutionized":[8],"image":[9],"understanding":[10,112],"by":[11,48],"providing":[12],"rich":[13],"semantic":[14,63,88],"features.":[15],"However,":[16],"despite":[17],"their":[18,23,51],"success":[19],"in":[20,127],"2D":[21],"comprehension,":[22],"abilities":[24],"on":[25,79,91,103,119],"grasping":[26],"3D":[27,41,55,73,104,110],"spatial":[28],"relationships":[29],"are":[30],"still":[31],"unclear.":[32],"In":[33],"this":[34,92],"work,":[35],"we":[36,94],"evaluate":[37],"and":[38,87],"enhance":[39],"awareness":[42],"of":[43,62,113],"ViT-based":[44],"models.":[45,116],"We":[46],"begin":[47],"systematically":[49],"assessing":[50],"ability":[52],"to":[53,76],"learn":[54],"equivariant":[56],"features,":[57],"specifically":[58],"examining":[59],"consistency":[61],"embeddings":[64],"across":[65],"different":[66],"viewpoints.":[67],"Our":[68,130],"findings":[69],"indicate":[70],"that":[71],"improved":[72],"equivariance":[74],"leads":[75],"better":[77],"performance":[78],"various":[80],"downstream":[81],"tasks,":[82],"including":[83],"pose":[84],"estimation,":[85],"tracking,":[86],"transfer.":[89],"Building":[90],"insight,":[93],"propose":[95],"a":[96,120],"simple":[97],"yet":[98],"effective":[99],"finetuning":[100,118],"strategy":[101],"based":[102],"correspondences,":[105],"which":[106],"significantly":[107],"enhances":[108],"correspondence":[111],"existing":[114],"vision":[115],"Remarkably,":[117],"single":[121],"object":[122],"for":[123],"one":[124],"iteration":[125],"results":[126],"substantial":[128],"gains.":[129],"code":[131],"is":[132],"available":[133],"at":[134],"https://github.com/qq456cvb/3DCorrEnhance.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-12-05T00:00:00"}