{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5A6V67NPR7FETSNDDZYFHFG5IB","short_pith_number":"pith:5A6V67NP","schema_version":"1.0","canonical_sha256":"e83d5f7daf8fca49c9a31e705394dd406045e5860b5ef02358b9df3038aef0e5","source":{"kind":"arxiv","id":"2404.11139","version":1},"attestation_state":"computed","paper":{"title":"GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ales Leonardis, Chen Wang, Hua Chen, Linfang Zheng, Tze Ho Elden Tse, Wei Zhang, Yinghan Sun","submitted_at":"2024-04-17T07:34:21Z","abstract_excerpt":"Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress towards instance-level object pose refinement. Yet, category-level pose refinement is a more challenging problem due to large shape variations within a category and the discrepancies between the target object and the shape prior. To address these challenges, we introduce a novel architecture for category-level object pose refinement. Our approach integrates an HS-layer and learnable affine transformations, which aims to enhance the extraction and alignment of geometric information"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.11139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T07:34:21Z","cross_cats_sorted":[],"title_canon_sha256":"a5a403ed69fe27beb092d1d098a3eeba11e071c1096ecf24245f791114ad85e0","abstract_canon_sha256":"b6a3829000dfef56905c80585fa4ce4f2889516f6e0db1c1a0ce9a68bcbfd9f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:04.639078Z","signature_b64":"u8iDASWPH1WgQoEtj0mhYmyhoj+tP5ibmCh4f3D2fXZGQrUBPsyZNGsXrg9eHIVESlOWtz08tFhPNeGVb/IMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e83d5f7daf8fca49c9a31e705394dd406045e5860b5ef02358b9df3038aef0e5","last_reissued_at":"2026-07-05T08:09:04.638633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:04.638633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ales Leonardis, Chen Wang, Hua Chen, Linfang Zheng, Tze Ho Elden Tse, Wei Zhang, Yinghan Sun","submitted_at":"2024-04-17T07:34:21Z","abstract_excerpt":"Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress towards instance-level object pose refinement. Yet, category-level pose refinement is a more challenging problem due to large shape variations within a category and the discrepancies between the target object and the shape prior. To address these challenges, we introduce a novel architecture for category-level object pose refinement. Our approach integrates an HS-layer and learnable affine transformations, which aims to enhance the extraction and alignment of geometric information"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11139","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.11139/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.11139","created_at":"2026-07-05T08:09:04.638692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11139v1","created_at":"2026-07-05T08:09:04.638692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11139","created_at":"2026-07-05T08:09:04.638692+00:00"},{"alias_kind":"pith_short_12","alias_value":"5A6V67NPR7FE","created_at":"2026-07-05T08:09:04.638692+00:00"},{"alias_kind":"pith_short_16","alias_value":"5A6V67NPR7FETSND","created_at":"2026-07-05T08:09:04.638692+00:00"},{"alias_kind":"pith_short_8","alias_value":"5A6V67NP","created_at":"2026-07-05T08:09:04.638692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00361","citing_title":"Generative Visual Foresight Meets Task-Agnostic Pose Estimation in Robotic Table-Top Manipulation","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5A6V67NPR7FETSNDDZYFHFG5IB","json":"https://pith.science/pith/5A6V67NPR7FETSNDDZYFHFG5IB.json","graph_json":"https://pith.science/api/pith-number/5A6V67NPR7FETSNDDZYFHFG5IB/graph.json","events_json":"https://pith.science/api/pith-number/5A6V67NPR7FETSNDDZYFHFG5IB/events.json","paper":"https://pith.science/paper/5A6V67NP"},"agent_actions":{"view_html":"https://pith.science/pith/5A6V67NPR7FETSNDDZYFHFG5IB","download_json":"https://pith.science/pith/5A6V67NPR7FETSNDDZYFHFG5IB.json","view_paper":"https://pith.science/paper/5A6V67NP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11139&json=true","fetch_graph":"https://pith.science/api/pith-number/5A6V67NPR7FETSNDDZYFHFG5IB/graph.json","fetch_events":"https://pith.science/api/pith-number/5A6V67NPR7FETSNDDZYFHFG5IB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5A6V67NPR7FETSNDDZYFHFG5IB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5A6V67NPR7FETSNDDZYFHFG5IB/action/storage_attestation","attest_author":"https://pith.science/pith/5A6V67NPR7FETSNDDZYFHFG5IB/action/author_attestation","sign_citation":"https://pith.science/pith/5A6V67NPR7FETSNDDZYFHFG5IB/action/citation_signature","submit_replication":"https://pith.science/pith/5A6V67NPR7FETSNDDZYFHFG5IB/action/replication_record"}},"created_at":"2026-07-05T08:09:04.638692+00:00","updated_at":"2026-07-05T08:09:04.638692+00:00"}