{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3CC3O24V6B4KYQZNXBKTHVYPUE","short_pith_number":"pith:3CC3O24V","schema_version":"1.0","canonical_sha256":"d885b76b95f078ac432db85533d70fa108ed38493d6436e83c109148e14b8002","source":{"kind":"arxiv","id":"2403.10683","version":2},"attestation_state":"computed","paper":{"title":"GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingding Cai, Esa Rahtu, Janne Heikkil\\\"a","submitted_at":"2024-03-15T21:06:14Z","abstract_excerpt":"This paper introduces GS-Pose, a unified framework for localizing and estimating the 6D pose of novel objects. GS-Pose begins with a set of posed RGB images of a previously unseen object and builds three distinct representations stored in a database. At inference, GS-Pose operates sequentially by locating the object in the input image, estimating its initial 6D pose using a retrieval approach, and refining the pose with a render-and-compare method. The key insight is the application of the appropriate object representation at each stage of the process. In particular, for the refinement step, w"},"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":"2403.10683","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T21:06:14Z","cross_cats_sorted":[],"title_canon_sha256":"4a3bdfac80073e81b6d23a3228249428fd1f5dbf123da7f9fc51045617d84d24","abstract_canon_sha256":"b9beea965fa933be1aac71ac43079b90c0c1e2565ee45bc5f495dd189c0e0de1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:22.274909Z","signature_b64":"XIjxQido1VbmQCVZazzli3Rz7etwD4f4WOSYHCZG998f4RxsJJLpbARQNan66lqa3E5ubIU/AYcZdhRirDwKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d885b76b95f078ac432db85533d70fa108ed38493d6436e83c109148e14b8002","last_reissued_at":"2026-07-05T08:55:22.274486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:22.274486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingding Cai, Esa Rahtu, Janne Heikkil\\\"a","submitted_at":"2024-03-15T21:06:14Z","abstract_excerpt":"This paper introduces GS-Pose, a unified framework for localizing and estimating the 6D pose of novel objects. GS-Pose begins with a set of posed RGB images of a previously unseen object and builds three distinct representations stored in a database. At inference, GS-Pose operates sequentially by locating the object in the input image, estimating its initial 6D pose using a retrieval approach, and refining the pose with a render-and-compare method. The key insight is the application of the appropriate object representation at each stage of the process. In particular, for the refinement step, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10683","kind":"arxiv","version":2},"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/2403.10683/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":"2403.10683","created_at":"2026-07-05T08:55:22.274551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10683v2","created_at":"2026-07-05T08:55:22.274551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10683","created_at":"2026-07-05T08:55:22.274551+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CC3O24V6B4K","created_at":"2026-07-05T08:55:22.274551+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CC3O24V6B4KYQZN","created_at":"2026-07-05T08:55:22.274551+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CC3O24V","created_at":"2026-07-05T08:55:22.274551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19498","citing_title":"T-Rex: Task-Adaptive Spatial Representation Extraction for Robotic Manipulation with Vision-Language Models","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3CC3O24V6B4KYQZNXBKTHVYPUE","json":"https://pith.science/pith/3CC3O24V6B4KYQZNXBKTHVYPUE.json","graph_json":"https://pith.science/api/pith-number/3CC3O24V6B4KYQZNXBKTHVYPUE/graph.json","events_json":"https://pith.science/api/pith-number/3CC3O24V6B4KYQZNXBKTHVYPUE/events.json","paper":"https://pith.science/paper/3CC3O24V"},"agent_actions":{"view_html":"https://pith.science/pith/3CC3O24V6B4KYQZNXBKTHVYPUE","download_json":"https://pith.science/pith/3CC3O24V6B4KYQZNXBKTHVYPUE.json","view_paper":"https://pith.science/paper/3CC3O24V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10683&json=true","fetch_graph":"https://pith.science/api/pith-number/3CC3O24V6B4KYQZNXBKTHVYPUE/graph.json","fetch_events":"https://pith.science/api/pith-number/3CC3O24V6B4KYQZNXBKTHVYPUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CC3O24V6B4KYQZNXBKTHVYPUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CC3O24V6B4KYQZNXBKTHVYPUE/action/storage_attestation","attest_author":"https://pith.science/pith/3CC3O24V6B4KYQZNXBKTHVYPUE/action/author_attestation","sign_citation":"https://pith.science/pith/3CC3O24V6B4KYQZNXBKTHVYPUE/action/citation_signature","submit_replication":"https://pith.science/pith/3CC3O24V6B4KYQZNXBKTHVYPUE/action/replication_record"}},"created_at":"2026-07-05T08:55:22.274551+00:00","updated_at":"2026-07-05T08:55:22.274551+00:00"}