{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YL7ZOHLQDFINAP53LG364PI54X","short_pith_number":"pith:YL7ZOHLQ","schema_version":"1.0","canonical_sha256":"c2ff971d701950d03fbb59b7ee3d1de5c105dbb30f514be3bf4c97fc1b1b0465","source":{"kind":"arxiv","id":"2402.14817","version":3},"attestation_state":"computed","paper":{"title":"Cameras as Rays: Pose Estimation via Ray Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amy Lin, Deva Ramanan, Jason Y. Zhang, Moneish Kumar, Shubham Tulsiani, Tzu-Hsuan Yang","submitted_at":"2024-02-22T18:59:56Z","abstract_excerpt":"Estimating camera poses is a fundamental task for 3D reconstruction and remains challenging given sparsely sampled views (<10). In contrast to existing approaches that pursue top-down prediction of global parametrizations of camera extrinsics, we propose a distributed representation of camera pose that treats a camera as a bundle of rays. This representation allows for a tight coupling with spatial image features improving pose precision. We observe that this representation is naturally suited for set-level transformers and develop a regression-based approach that maps image patches to corresp"},"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":"2402.14817","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T18:59:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3410b84d35b64d81bdc70c7ddeaec56968f5856d55f76673f401d68c298393a9","abstract_canon_sha256":"e03ee8b5dc198f84e645baffa0ce7f8685ffd55a6928949d56292edbc94b7167"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:18.269465Z","signature_b64":"UpcoYDDRkCdBYQi1nDZeQX3Q2W5mdaOT4ehqrFB0+C9V7qSZvq3rxG3jx1CyfNswdw9vQXM/YXHvx7vPlRKwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2ff971d701950d03fbb59b7ee3d1de5c105dbb30f514be3bf4c97fc1b1b0465","last_reissued_at":"2026-07-05T08:04:18.269006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:18.269006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cameras as Rays: Pose Estimation via Ray Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amy Lin, Deva Ramanan, Jason Y. Zhang, Moneish Kumar, Shubham Tulsiani, Tzu-Hsuan Yang","submitted_at":"2024-02-22T18:59:56Z","abstract_excerpt":"Estimating camera poses is a fundamental task for 3D reconstruction and remains challenging given sparsely sampled views (<10). In contrast to existing approaches that pursue top-down prediction of global parametrizations of camera extrinsics, we propose a distributed representation of camera pose that treats a camera as a bundle of rays. This representation allows for a tight coupling with spatial image features improving pose precision. We observe that this representation is naturally suited for set-level transformers and develop a regression-based approach that maps image patches to corresp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14817","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/2402.14817/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":"2402.14817","created_at":"2026-07-05T08:04:18.269056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14817v3","created_at":"2026-07-05T08:04:18.269056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14817","created_at":"2026-07-05T08:04:18.269056+00:00"},{"alias_kind":"pith_short_12","alias_value":"YL7ZOHLQDFIN","created_at":"2026-07-05T08:04:18.269056+00:00"},{"alias_kind":"pith_short_16","alias_value":"YL7ZOHLQDFINAP53","created_at":"2026-07-05T08:04:18.269056+00:00"},{"alias_kind":"pith_short_8","alias_value":"YL7ZOHLQ","created_at":"2026-07-05T08:04:18.269056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05376","citing_title":"MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.26103","citing_title":"Global Structure-from-Motion Meets Feedforward Reconstruction","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12938","citing_title":"CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08500","citing_title":"Novel View Synthesis as Video Completion","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YL7ZOHLQDFINAP53LG364PI54X","json":"https://pith.science/pith/YL7ZOHLQDFINAP53LG364PI54X.json","graph_json":"https://pith.science/api/pith-number/YL7ZOHLQDFINAP53LG364PI54X/graph.json","events_json":"https://pith.science/api/pith-number/YL7ZOHLQDFINAP53LG364PI54X/events.json","paper":"https://pith.science/paper/YL7ZOHLQ"},"agent_actions":{"view_html":"https://pith.science/pith/YL7ZOHLQDFINAP53LG364PI54X","download_json":"https://pith.science/pith/YL7ZOHLQDFINAP53LG364PI54X.json","view_paper":"https://pith.science/paper/YL7ZOHLQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14817&json=true","fetch_graph":"https://pith.science/api/pith-number/YL7ZOHLQDFINAP53LG364PI54X/graph.json","fetch_events":"https://pith.science/api/pith-number/YL7ZOHLQDFINAP53LG364PI54X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YL7ZOHLQDFINAP53LG364PI54X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YL7ZOHLQDFINAP53LG364PI54X/action/storage_attestation","attest_author":"https://pith.science/pith/YL7ZOHLQDFINAP53LG364PI54X/action/author_attestation","sign_citation":"https://pith.science/pith/YL7ZOHLQDFINAP53LG364PI54X/action/citation_signature","submit_replication":"https://pith.science/pith/YL7ZOHLQDFINAP53LG364PI54X/action/replication_record"}},"created_at":"2026-07-05T08:04:18.269056+00:00","updated_at":"2026-07-05T08:04:18.269056+00:00"}