{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FFCXDGE4HFFKWLA272SCXVA3QB","short_pith_number":"pith:FFCXDGE4","schema_version":"1.0","canonical_sha256":"294571989c394aab2c1afea42bd41b805c75d212c03455155e284c7371396d86","source":{"kind":"arxiv","id":"1704.00390","version":2},"attestation_state":"computed","paper":{"title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Kendall, Roberto Cipolla","submitted_at":"2017-04-02T23:58:22Z","abstract_excerpt":"Deep learning has shown to be effective for robust and real-time monocular image relocalisation. In particular, PoseNet is a deep convolutional neural network which learns to regress the 6-DOF camera pose from a single image. It learns to localize using high level features and is robust to difficult lighting, motion blur and unknown camera intrinsics, where point based SIFT registration fails. However, it was trained using a naive loss function, with hyper-parameters which require expensive tuning. In this paper, we give the problem a more fundamental theoretical treatment. We explore a number"},"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":"1704.00390","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-02T23:58:22Z","cross_cats_sorted":[],"title_canon_sha256":"74c6a8ce7c45021e04a1340a6c811dddd23b9b176ec6bc616b9fb7fef0d9846e","abstract_canon_sha256":"91867ba8c5c19fe674a542d5e118693e912896e4d327f49137d83cae8457459c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:51.032687Z","signature_b64":"64z+Ja5F7th+W6dn1gpX/96EiQ0VLDUOjkHMErL3c7YE4Nxax2LKPU6m04sp9YNp2I2D57uYKBuNiy3xg3YZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"294571989c394aab2c1afea42bd41b805c75d212c03455155e284c7371396d86","last_reissued_at":"2026-05-18T00:43:51.032025Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:51.032025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Kendall, Roberto Cipolla","submitted_at":"2017-04-02T23:58:22Z","abstract_excerpt":"Deep learning has shown to be effective for robust and real-time monocular image relocalisation. In particular, PoseNet is a deep convolutional neural network which learns to regress the 6-DOF camera pose from a single image. It learns to localize using high level features and is robust to difficult lighting, motion blur and unknown camera intrinsics, where point based SIFT registration fails. However, it was trained using a naive loss function, with hyper-parameters which require expensive tuning. In this paper, we give the problem a more fundamental theoretical treatment. We explore a number"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.00390","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":""},"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":"1704.00390","created_at":"2026-05-18T00:43:51.032134+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.00390v2","created_at":"2026-05-18T00:43:51.032134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00390","created_at":"2026-05-18T00:43:51.032134+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFCXDGE4HFFK","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFCXDGE4HFFKWLA2","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFCXDGE4","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.09236","citing_title":"RGB-D image-based Object Detection: from Traditional Methods to Deep Learning Techniques","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFCXDGE4HFFKWLA272SCXVA3QB","json":"https://pith.science/pith/FFCXDGE4HFFKWLA272SCXVA3QB.json","graph_json":"https://pith.science/api/pith-number/FFCXDGE4HFFKWLA272SCXVA3QB/graph.json","events_json":"https://pith.science/api/pith-number/FFCXDGE4HFFKWLA272SCXVA3QB/events.json","paper":"https://pith.science/paper/FFCXDGE4"},"agent_actions":{"view_html":"https://pith.science/pith/FFCXDGE4HFFKWLA272SCXVA3QB","download_json":"https://pith.science/pith/FFCXDGE4HFFKWLA272SCXVA3QB.json","view_paper":"https://pith.science/paper/FFCXDGE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.00390&json=true","fetch_graph":"https://pith.science/api/pith-number/FFCXDGE4HFFKWLA272SCXVA3QB/graph.json","fetch_events":"https://pith.science/api/pith-number/FFCXDGE4HFFKWLA272SCXVA3QB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFCXDGE4HFFKWLA272SCXVA3QB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFCXDGE4HFFKWLA272SCXVA3QB/action/storage_attestation","attest_author":"https://pith.science/pith/FFCXDGE4HFFKWLA272SCXVA3QB/action/author_attestation","sign_citation":"https://pith.science/pith/FFCXDGE4HFFKWLA272SCXVA3QB/action/citation_signature","submit_replication":"https://pith.science/pith/FFCXDGE4HFFKWLA272SCXVA3QB/action/replication_record"}},"created_at":"2026-05-18T00:43:51.032134+00:00","updated_at":"2026-05-18T00:43:51.032134+00:00"}