{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RXCN3P3CFJURM4UK2A6Q47KYIO","short_pith_number":"pith:RXCN3P3C","schema_version":"1.0","canonical_sha256":"8dc4ddbf622a6916728ad03d0e7d58438d98ba1e01cc887e0a9e210b78622c3d","source":{"kind":"arxiv","id":"2404.15259","version":3},"attestation_state":"computed","paper":{"title":"FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayush Tewari, Cameron Smith, David Charatan, Vincent Sitzmann","submitted_at":"2024-04-23T17:46:50Z","abstract_excerpt":"This paper introduces FlowMap, an end-to-end differentiable method that solves for precise camera poses, camera intrinsics, and per-frame dense depth of a video sequence. Our method performs per-video gradient-descent minimization of a simple least-squares objective that compares the optical flow induced by depth, intrinsics, and poses against correspondences obtained via off-the-shelf optical flow and point tracking. Alongside the use of point tracks to encourage long-term geometric consistency, we introduce differentiable re-parameterizations of depth, intrinsics, and pose that are amenable "},"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":"2404.15259","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-23T17:46:50Z","cross_cats_sorted":[],"title_canon_sha256":"c7d0358a9b08335f24dcf35c778bdf404245ffe3a98b7f2cae7c9e91bfd74f99","abstract_canon_sha256":"0117434544daa5ceb4c17cb7b8b060b71917edec76f4510f073c6f685b52809a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:19.280849Z","signature_b64":"z5dAv8NDr7FWGN0mv7PqZCuzyNeL0g7YBrjaKhcOI49kx0tCHiSyfTjdA6MjYBh+U+UHGojCcs4yis87w/HFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dc4ddbf622a6916728ad03d0e7d58438d98ba1e01cc887e0a9e210b78622c3d","last_reissued_at":"2026-07-05T08:47:19.280353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:19.280353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayush Tewari, Cameron Smith, David Charatan, Vincent Sitzmann","submitted_at":"2024-04-23T17:46:50Z","abstract_excerpt":"This paper introduces FlowMap, an end-to-end differentiable method that solves for precise camera poses, camera intrinsics, and per-frame dense depth of a video sequence. Our method performs per-video gradient-descent minimization of a simple least-squares objective that compares the optical flow induced by depth, intrinsics, and poses against correspondences obtained via off-the-shelf optical flow and point tracking. Alongside the use of point tracks to encourage long-term geometric consistency, we introduce differentiable re-parameterizations of depth, intrinsics, and pose that are amenable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15259","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/2404.15259/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":"2404.15259","created_at":"2026-07-05T08:47:19.280413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15259v3","created_at":"2026-07-05T08:47:19.280413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15259","created_at":"2026-07-05T08:47:19.280413+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXCN3P3CFJUR","created_at":"2026-07-05T08:47:19.280413+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXCN3P3CFJURM4UK","created_at":"2026-07-05T08:47:19.280413+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXCN3P3C","created_at":"2026-07-05T08:47:19.280413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":207,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19727","citing_title":"Tango3D: Towards Alignment for Global and Local 2D-3D Correspondence","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16443","citing_title":"VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXCN3P3CFJURM4UK2A6Q47KYIO","json":"https://pith.science/pith/RXCN3P3CFJURM4UK2A6Q47KYIO.json","graph_json":"https://pith.science/api/pith-number/RXCN3P3CFJURM4UK2A6Q47KYIO/graph.json","events_json":"https://pith.science/api/pith-number/RXCN3P3CFJURM4UK2A6Q47KYIO/events.json","paper":"https://pith.science/paper/RXCN3P3C"},"agent_actions":{"view_html":"https://pith.science/pith/RXCN3P3CFJURM4UK2A6Q47KYIO","download_json":"https://pith.science/pith/RXCN3P3CFJURM4UK2A6Q47KYIO.json","view_paper":"https://pith.science/paper/RXCN3P3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15259&json=true","fetch_graph":"https://pith.science/api/pith-number/RXCN3P3CFJURM4UK2A6Q47KYIO/graph.json","fetch_events":"https://pith.science/api/pith-number/RXCN3P3CFJURM4UK2A6Q47KYIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXCN3P3CFJURM4UK2A6Q47KYIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXCN3P3CFJURM4UK2A6Q47KYIO/action/storage_attestation","attest_author":"https://pith.science/pith/RXCN3P3CFJURM4UK2A6Q47KYIO/action/author_attestation","sign_citation":"https://pith.science/pith/RXCN3P3CFJURM4UK2A6Q47KYIO/action/citation_signature","submit_replication":"https://pith.science/pith/RXCN3P3CFJURM4UK2A6Q47KYIO/action/replication_record"}},"created_at":"2026-07-05T08:47:19.280413+00:00","updated_at":"2026-07-05T08:47:19.280413+00:00"}