{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HU7S7RDWBSXDCB7TDONODRQAQP","short_pith_number":"pith:HU7S7RDW","schema_version":"1.0","canonical_sha256":"3d3f2fc4760cae3107f31b9ae1c60083d9b03b4ded4b1c8a60b3e617f0face26","source":{"kind":"arxiv","id":"2007.13867","version":3},"attestation_state":"computed","paper":{"title":"Robust Image Retrieval-based Visual Localization using Kapture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cesar de Souza, Gabriela Csurka, J\\'er\\^ome Revaud, Julien Morat, Martin Humenberger, Nicolas Guerin, No\\'e Pion, Philippe Rerole, Vincent Leroy, Yohann Cabon","submitted_at":"2020-07-27T21:10:35Z","abstract_excerpt":"Visual localization tackles the challenge of estimating the camera pose from images by using correspondence analysis between query images and a map. This task is computation and data intensive which poses challenges on thorough evaluation of methods on various datasets. However, in order to further advance in the field, we claim that robust visual localization algorithms should be evaluated on multiple datasets covering a broad domain variety. To facilitate this, we introduce kapture, a new, flexible, unified data format and toolbox for visual localization and structure-from-motion (SFM). It e"},"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":"2007.13867","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-27T21:10:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b637cc2c8c4b6af74d211767cb4ca88ec1717e1f782d3208734d865d44241372","abstract_canon_sha256":"5225e1c05497735a221bd716445f777b6d210bdef92d1da1544cdc106d2ef5ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:32.271746Z","signature_b64":"jEZZs8nGiNOPJ5sXJqqag+RYZfMDxjFHuprbgNF7UEKLaSwFiRycO2zF2MjFQ4Jj34XECOY1pxtcmAJHCAdEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d3f2fc4760cae3107f31b9ae1c60083d9b03b4ded4b1c8a60b3e617f0face26","last_reissued_at":"2026-07-05T03:46:32.271236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:32.271236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Image Retrieval-based Visual Localization using Kapture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cesar de Souza, Gabriela Csurka, J\\'er\\^ome Revaud, Julien Morat, Martin Humenberger, Nicolas Guerin, No\\'e Pion, Philippe Rerole, Vincent Leroy, Yohann Cabon","submitted_at":"2020-07-27T21:10:35Z","abstract_excerpt":"Visual localization tackles the challenge of estimating the camera pose from images by using correspondence analysis between query images and a map. This task is computation and data intensive which poses challenges on thorough evaluation of methods on various datasets. However, in order to further advance in the field, we claim that robust visual localization algorithms should be evaluated on multiple datasets covering a broad domain variety. To facilitate this, we introduce kapture, a new, flexible, unified data format and toolbox for visual localization and structure-from-motion (SFM). It e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13867","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/2007.13867/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":"2007.13867","created_at":"2026-07-05T03:46:32.271293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.13867v3","created_at":"2026-07-05T03:46:32.271293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13867","created_at":"2026-07-05T03:46:32.271293+00:00"},{"alias_kind":"pith_short_12","alias_value":"HU7S7RDWBSXD","created_at":"2026-07-05T03:46:32.271293+00:00"},{"alias_kind":"pith_short_16","alias_value":"HU7S7RDWBSXDCB7T","created_at":"2026-07-05T03:46:32.271293+00:00"},{"alias_kind":"pith_short_8","alias_value":"HU7S7RDW","created_at":"2026-07-05T03:46:32.271293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.13864","citing_title":"GRLoc: Geometric Representation Regression for Visual Localization","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00978","citing_title":"A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03814","citing_title":"InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Dataset","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00562","citing_title":"Depth-Guided Privacy-Preserving Visual Localization Using 3D Sphere Clouds","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07351","citing_title":"Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HU7S7RDWBSXDCB7TDONODRQAQP","json":"https://pith.science/pith/HU7S7RDWBSXDCB7TDONODRQAQP.json","graph_json":"https://pith.science/api/pith-number/HU7S7RDWBSXDCB7TDONODRQAQP/graph.json","events_json":"https://pith.science/api/pith-number/HU7S7RDWBSXDCB7TDONODRQAQP/events.json","paper":"https://pith.science/paper/HU7S7RDW"},"agent_actions":{"view_html":"https://pith.science/pith/HU7S7RDWBSXDCB7TDONODRQAQP","download_json":"https://pith.science/pith/HU7S7RDWBSXDCB7TDONODRQAQP.json","view_paper":"https://pith.science/paper/HU7S7RDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.13867&json=true","fetch_graph":"https://pith.science/api/pith-number/HU7S7RDWBSXDCB7TDONODRQAQP/graph.json","fetch_events":"https://pith.science/api/pith-number/HU7S7RDWBSXDCB7TDONODRQAQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HU7S7RDWBSXDCB7TDONODRQAQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HU7S7RDWBSXDCB7TDONODRQAQP/action/storage_attestation","attest_author":"https://pith.science/pith/HU7S7RDWBSXDCB7TDONODRQAQP/action/author_attestation","sign_citation":"https://pith.science/pith/HU7S7RDWBSXDCB7TDONODRQAQP/action/citation_signature","submit_replication":"https://pith.science/pith/HU7S7RDWBSXDCB7TDONODRQAQP/action/replication_record"}},"created_at":"2026-07-05T03:46:32.271293+00:00","updated_at":"2026-07-05T03:46:32.271293+00:00"}