{"id":"https://openalex.org/W4417296911","doi":"https://doi.org/10.48550/arxiv.2512.10840","title":"PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning","display_name":"PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning","publication_year":2025,"publication_date":"2025-12-11","ids":{"openalex":"https://openalex.org/W4417296911","doi":"https://doi.org/10.48550/arxiv.2512.10840"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2512.10840","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10840","pdf_url":"https://arxiv.org/pdf/2512.10840","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.10840","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101622033","display_name":"Jianqi Chen","orcid":"https://orcid.org/0000-0003-4438-4467"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Jianqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363706","display_name":"Biao Zhang","orcid":"https://orcid.org/0000-0001-5685-6092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Biao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087452083","display_name":"Xiangjun Tang","orcid":"https://orcid.org/0000-0001-7441-0086"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Xiangjun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076768552","display_name":"Peter Wonka","orcid":"https://orcid.org/0000-0003-0627-9746"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wonka, Peter","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101622033"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.788100004196167,"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":0.788100004196167,"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":0.04560000076889992,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.042500000447034836,"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":[],"concepts":[],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.10840","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10840","pdf_url":"https://arxiv.org/pdf/2512.10840","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2512.10840","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.10840","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.10840","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10840","pdf_url":"https://arxiv.org/pdf/2512.10840","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"6D":[0],"object":[1,10,36,54,80],"pose":[2,55],"estimation,":[3],"which":[4],"predicts":[5,53],"the":[6,13,30,35,65,77],"transformation":[7],"of":[8,133],"an":[9,129],"relative":[11],"to":[12,114,141,150],"camera,":[14],"remains":[15],"challenging":[16],"for":[17,67],"unseen":[18,151],"objects.":[19,152],"Existing":[20],"approaches":[21],"typically":[22],"rely":[23],"on":[24,144],"explicitly":[25],"constructing":[26],"feature":[27],"correspondences":[28],"between":[29],"query":[31,58],"image":[32,59],"and":[33,60,90,117,138],"either":[34],"model":[37,75],"or":[38],"template":[39,62],"images.":[40],"In":[41,97],"this":[42],"work,":[43],"we":[44,99],"propose":[45],"PoseGAM,":[46],"a":[47,57,101],"geometry-aware":[48],"multi-view":[49],"framework":[50],"that":[51],"directly":[52],"from":[56,93],"multiple":[61,122],"images,":[63],"eliminating":[64],"need":[66],"explicit":[68,87],"matching.":[69],"Built":[70],"upon":[71],"recent":[72],"multi-view-based":[73],"foundation":[74],"architectures,":[76],"method":[78],"integrates":[79],"geometry":[81,89,94],"information":[82],"through":[83],"two":[84],"complementary":[85],"mechanisms:":[86],"point-based":[88],"learned":[91],"features":[92],"representation":[95],"networks.":[96],"addition,":[98],"construct":[100],"large-scale":[102],"synthetic":[103],"dataset":[104],"containing":[105],"more":[106],"than":[107],"190k":[108],"objects":[109],"under":[110],"diverse":[111],"environmental":[112],"conditions":[113],"enhance":[115],"robustness":[116],"generalization.":[118],"Extensive":[119],"evaluations":[120],"across":[121],"benchmarks":[123],"demonstrate":[124],"our":[125],"state-of-the-art":[126],"performance,":[127],"yielding":[128],"average":[130],"AR":[131],"improvement":[132],"5.1%":[134],"over":[135],"prior":[136],"methods":[137],"achieving":[139],"up":[140],"17.6%":[142],"gains":[143],"individual":[145],"datasets,":[146],"indicating":[147],"strong":[148],"generalization":[149],"Project":[153],"page:":[154],"https://windvchen.github.io/PoseGAM/":[155],".":[156]},"counts_by_year":[],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-12-13T00:00:00"}