{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EHFKBTQWACAERUHIV2A3LWF7L2","short_pith_number":"pith:EHFKBTQW","schema_version":"1.0","canonical_sha256":"21caa0ce16008048d0e8ae81b5d8bf5e85c88f99857e7a3850221b3090673311","source":{"kind":"arxiv","id":"2411.03807","version":3},"attestation_state":"computed","paper":{"title":"GS2Pose: Two-stage 6D Object Pose Estimation Guided by Gaussian Splatting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cai Meng, Jilan Mei, Junbo Li","submitted_at":"2024-11-06T10:07:46Z","abstract_excerpt":"This paper proposes a new method for accurate and robust 6D pose estimation of novel objects, named GS2Pose. By introducing 3D Gaussian splatting, GS2Pose can utilize the reconstruction results without requiring a high-quality CAD model, which means it only requires segmented RGBD images as input. Specifically, GS2Pose employs a two-stage structure consisting of coarse estimation followed by refined estimation. In the coarse stage, a lightweight U-Net network with a polarization attention mechanism, called Pose-Net, is designed. By using the 3DGS model for supervised training, Pose-Net can gen"},"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":"2411.03807","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-06T10:07:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0e81e7a37985c05afc337a8a90ac6af5e198d4f2f1aa7b2db043666299f2f46f","abstract_canon_sha256":"8f5ed6209dc26fae73f68da4b9834a44e2d8f9523a3b5fa2dce74f13b75b6c50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:50.297692Z","signature_b64":"2FHwZL2ih2PqhYwoANCf23xngmHOyTFsGGzPZX89QhtgpwQO+O82EQlzOMB1lbb0pLXoxWIRlLABZCywA5LSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21caa0ce16008048d0e8ae81b5d8bf5e85c88f99857e7a3850221b3090673311","last_reissued_at":"2026-07-05T09:32:50.297150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:50.297150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GS2Pose: Two-stage 6D Object Pose Estimation Guided by Gaussian Splatting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cai Meng, Jilan Mei, Junbo Li","submitted_at":"2024-11-06T10:07:46Z","abstract_excerpt":"This paper proposes a new method for accurate and robust 6D pose estimation of novel objects, named GS2Pose. By introducing 3D Gaussian splatting, GS2Pose can utilize the reconstruction results without requiring a high-quality CAD model, which means it only requires segmented RGBD images as input. Specifically, GS2Pose employs a two-stage structure consisting of coarse estimation followed by refined estimation. In the coarse stage, a lightweight U-Net network with a polarization attention mechanism, called Pose-Net, is designed. By using the 3DGS model for supervised training, Pose-Net can gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03807","kind":"arxiv","version":3},"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/2411.03807/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":"2411.03807","created_at":"2026-07-05T09:32:50.297213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03807v3","created_at":"2026-07-05T09:32:50.297213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03807","created_at":"2026-07-05T09:32:50.297213+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHFKBTQWACAE","created_at":"2026-07-05T09:32:50.297213+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHFKBTQWACAERUHI","created_at":"2026-07-05T09:32:50.297213+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHFKBTQW","created_at":"2026-07-05T09:32:50.297213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08137","citing_title":"Occlusion-Aware Temporally Consistent Amodal Completion for 3D Human-Object Interaction Reconstruction","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHFKBTQWACAERUHIV2A3LWF7L2","json":"https://pith.science/pith/EHFKBTQWACAERUHIV2A3LWF7L2.json","graph_json":"https://pith.science/api/pith-number/EHFKBTQWACAERUHIV2A3LWF7L2/graph.json","events_json":"https://pith.science/api/pith-number/EHFKBTQWACAERUHIV2A3LWF7L2/events.json","paper":"https://pith.science/paper/EHFKBTQW"},"agent_actions":{"view_html":"https://pith.science/pith/EHFKBTQWACAERUHIV2A3LWF7L2","download_json":"https://pith.science/pith/EHFKBTQWACAERUHIV2A3LWF7L2.json","view_paper":"https://pith.science/paper/EHFKBTQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03807&json=true","fetch_graph":"https://pith.science/api/pith-number/EHFKBTQWACAERUHIV2A3LWF7L2/graph.json","fetch_events":"https://pith.science/api/pith-number/EHFKBTQWACAERUHIV2A3LWF7L2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHFKBTQWACAERUHIV2A3LWF7L2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHFKBTQWACAERUHIV2A3LWF7L2/action/storage_attestation","attest_author":"https://pith.science/pith/EHFKBTQWACAERUHIV2A3LWF7L2/action/author_attestation","sign_citation":"https://pith.science/pith/EHFKBTQWACAERUHIV2A3LWF7L2/action/citation_signature","submit_replication":"https://pith.science/pith/EHFKBTQWACAERUHIV2A3LWF7L2/action/replication_record"}},"created_at":"2026-07-05T09:32:50.297213+00:00","updated_at":"2026-07-05T09:32:50.297213+00:00"}