{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LZSZWE5EXFI2NKEBEMBSHCRHOC","short_pith_number":"pith:LZSZWE5E","schema_version":"1.0","canonical_sha256":"5e659b13a4b951a6a8812303238a2770889b4d36fba03cd82ddf17a6db79fbf3","source":{"kind":"arxiv","id":"2408.11085","version":4},"attestation_state":"computed","paper":{"title":"GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changkun Liu, Ming Cheng, Shuai Chen, Siyan Hu, Tristan Braud, Victor Adrian Prisacariu, Yash Bhalgat, Zirui Wang","submitted_at":"2024-08-20T17:58:23Z","abstract_excerpt":"We leverage 3D Gaussian Splatting (3DGS) as a scene representation and propose a novel test-time camera pose refinement (CPR) framework, GS-CPR. This framework enhances the localization accuracy of state-of-the-art absolute pose regression and scene coordinate regression methods. The 3DGS model renders high-quality synthetic images and depth maps to facilitate the establishment of 2D-3D correspondences. GS-CPR obviates the need for training feature extractors or descriptors by operating directly on RGB images, utilizing the 3D foundation model, MASt3R, for precise 2D matching. To improve the r"},"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":"2408.11085","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-20T17:58:23Z","cross_cats_sorted":[],"title_canon_sha256":"9d8f324abbece89f793b739abb1b904ec003526451af89464bc0af60f7e84bf2","abstract_canon_sha256":"4a255bd621a386b713a8dbb3800c29df504dd0d5be572fa1d7099d941967c952"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:03.425081Z","signature_b64":"/FO121KsLyrcCbdiSlvFOlIh+V4VtoDMqZJXKHLWHi137hLbOZvW2Y34oamG8V1v4E0YrNc8zAbWkTqfIaV6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e659b13a4b951a6a8812303238a2770889b4d36fba03cd82ddf17a6db79fbf3","last_reissued_at":"2026-07-05T10:22:03.424541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:03.424541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changkun Liu, Ming Cheng, Shuai Chen, Siyan Hu, Tristan Braud, Victor Adrian Prisacariu, Yash Bhalgat, Zirui Wang","submitted_at":"2024-08-20T17:58:23Z","abstract_excerpt":"We leverage 3D Gaussian Splatting (3DGS) as a scene representation and propose a novel test-time camera pose refinement (CPR) framework, GS-CPR. This framework enhances the localization accuracy of state-of-the-art absolute pose regression and scene coordinate regression methods. The 3DGS model renders high-quality synthetic images and depth maps to facilitate the establishment of 2D-3D correspondences. GS-CPR obviates the need for training feature extractors or descriptors by operating directly on RGB images, utilizing the 3D foundation model, MASt3R, for precise 2D matching. To improve the r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11085","kind":"arxiv","version":4},"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/2408.11085/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":"2408.11085","created_at":"2026-07-05T10:22:03.424599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11085v4","created_at":"2026-07-05T10:22:03.424599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11085","created_at":"2026-07-05T10:22:03.424599+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZSZWE5EXFI2","created_at":"2026-07-05T10:22:03.424599+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZSZWE5EXFI2NKEB","created_at":"2026-07-05T10:22:03.424599+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZSZWE5E","created_at":"2026-07-05T10:22:03.424599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.13864","citing_title":"GRLoc: Geometric Representation Regression for Visual Localization","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05402","citing_title":"LSGS-Loc: Towards Robust 3DGS-Based Visual Localization for Large-Scale UAV Scenarios","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZSZWE5EXFI2NKEBEMBSHCRHOC","json":"https://pith.science/pith/LZSZWE5EXFI2NKEBEMBSHCRHOC.json","graph_json":"https://pith.science/api/pith-number/LZSZWE5EXFI2NKEBEMBSHCRHOC/graph.json","events_json":"https://pith.science/api/pith-number/LZSZWE5EXFI2NKEBEMBSHCRHOC/events.json","paper":"https://pith.science/paper/LZSZWE5E"},"agent_actions":{"view_html":"https://pith.science/pith/LZSZWE5EXFI2NKEBEMBSHCRHOC","download_json":"https://pith.science/pith/LZSZWE5EXFI2NKEBEMBSHCRHOC.json","view_paper":"https://pith.science/paper/LZSZWE5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11085&json=true","fetch_graph":"https://pith.science/api/pith-number/LZSZWE5EXFI2NKEBEMBSHCRHOC/graph.json","fetch_events":"https://pith.science/api/pith-number/LZSZWE5EXFI2NKEBEMBSHCRHOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZSZWE5EXFI2NKEBEMBSHCRHOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZSZWE5EXFI2NKEBEMBSHCRHOC/action/storage_attestation","attest_author":"https://pith.science/pith/LZSZWE5EXFI2NKEBEMBSHCRHOC/action/author_attestation","sign_citation":"https://pith.science/pith/LZSZWE5EXFI2NKEBEMBSHCRHOC/action/citation_signature","submit_replication":"https://pith.science/pith/LZSZWE5EXFI2NKEBEMBSHCRHOC/action/replication_record"}},"created_at":"2026-07-05T10:22:03.424599+00:00","updated_at":"2026-07-05T10:22:03.424599+00:00"}