{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MA2POVR6WKHLCWYTKNGKKZKHZK","short_pith_number":"pith:MA2POVR6","schema_version":"1.0","canonical_sha256":"6034f7563eb28eb15b13534ca56547cab9cc4a51c61ee06ad3b334d984f8eef0","source":{"kind":"arxiv","id":"2108.07260","version":1},"attestation_state":"computed","paper":{"title":"Reassessing the Limitations of CNN Methods for Camera Pose Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian Lopez-Rodriguez, Krystian Mikolajczyk, Tony Ng, Vassileios Balntas","submitted_at":"2021-08-16T17:55:26Z","abstract_excerpt":"In this paper, we address the problem of camera pose estimation in outdoor and indoor scenarios. In comparison to the currently top-performing methods that rely on 2D to 3D matching, we propose a model that can directly regress the camera pose from images with significantly higher accuracy than existing methods of the same class. We first analyse why regression methods are still behind the state-of-the-art, and we bridge the performance gap with our new approach. Specifically, we propose a way to overcome the biased training data by a novel training technique, which generates poses guided by a"},"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":"2108.07260","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-16T17:55:26Z","cross_cats_sorted":[],"title_canon_sha256":"5462e4fb478926b14d64c3ac8b31a134dcccbe28fbb93223b24c4d84d5e780a9","abstract_canon_sha256":"ee3f42e23bf8f0999514b1f2844613920562b74240b9f970f53e02c40fc67687"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:02.966237Z","signature_b64":"bbc1IbZTql7lXPJKvni7TpeyCkUEl3R5Dsahixa+SnNLthJDnItciSGbxWky/HWFHQa/G/DZ6+Ky88gRbi+WBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6034f7563eb28eb15b13534ca56547cab9cc4a51c61ee06ad3b334d984f8eef0","last_reissued_at":"2026-07-05T03:06:02.965890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:02.965890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reassessing the Limitations of CNN Methods for Camera Pose Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian Lopez-Rodriguez, Krystian Mikolajczyk, Tony Ng, Vassileios Balntas","submitted_at":"2021-08-16T17:55:26Z","abstract_excerpt":"In this paper, we address the problem of camera pose estimation in outdoor and indoor scenarios. In comparison to the currently top-performing methods that rely on 2D to 3D matching, we propose a model that can directly regress the camera pose from images with significantly higher accuracy than existing methods of the same class. We first analyse why regression methods are still behind the state-of-the-art, and we bridge the performance gap with our new approach. Specifically, we propose a way to overcome the biased training data by a novel training technique, which generates poses guided by a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.07260","kind":"arxiv","version":1},"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/2108.07260/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":"2108.07260","created_at":"2026-07-05T03:06:02.965949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.07260v1","created_at":"2026-07-05T03:06:02.965949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.07260","created_at":"2026-07-05T03:06:02.965949+00:00"},{"alias_kind":"pith_short_12","alias_value":"MA2POVR6WKHL","created_at":"2026-07-05T03:06:02.965949+00:00"},{"alias_kind":"pith_short_16","alias_value":"MA2POVR6WKHLCWYT","created_at":"2026-07-05T03:06:02.965949+00:00"},{"alias_kind":"pith_short_8","alias_value":"MA2POVR6","created_at":"2026-07-05T03:06:02.965949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12027","citing_title":"SGLoc: Semantic Localization System for Camera Pose Estimation from 3D Gaussian Splatting Representation","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MA2POVR6WKHLCWYTKNGKKZKHZK","json":"https://pith.science/pith/MA2POVR6WKHLCWYTKNGKKZKHZK.json","graph_json":"https://pith.science/api/pith-number/MA2POVR6WKHLCWYTKNGKKZKHZK/graph.json","events_json":"https://pith.science/api/pith-number/MA2POVR6WKHLCWYTKNGKKZKHZK/events.json","paper":"https://pith.science/paper/MA2POVR6"},"agent_actions":{"view_html":"https://pith.science/pith/MA2POVR6WKHLCWYTKNGKKZKHZK","download_json":"https://pith.science/pith/MA2POVR6WKHLCWYTKNGKKZKHZK.json","view_paper":"https://pith.science/paper/MA2POVR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.07260&json=true","fetch_graph":"https://pith.science/api/pith-number/MA2POVR6WKHLCWYTKNGKKZKHZK/graph.json","fetch_events":"https://pith.science/api/pith-number/MA2POVR6WKHLCWYTKNGKKZKHZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MA2POVR6WKHLCWYTKNGKKZKHZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MA2POVR6WKHLCWYTKNGKKZKHZK/action/storage_attestation","attest_author":"https://pith.science/pith/MA2POVR6WKHLCWYTKNGKKZKHZK/action/author_attestation","sign_citation":"https://pith.science/pith/MA2POVR6WKHLCWYTKNGKKZKHZK/action/citation_signature","submit_replication":"https://pith.science/pith/MA2POVR6WKHLCWYTKNGKKZKHZK/action/replication_record"}},"created_at":"2026-07-05T03:06:02.965949+00:00","updated_at":"2026-07-05T03:06:02.965949+00:00"}