{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:FDEJ3L4RPR4OSATOB2AIUCNRFV","short_pith_number":"pith:FDEJ3L4R","schema_version":"1.0","canonical_sha256":"28c89daf917c78e9026e0e808a09b12d7074a66e401b49934b4e3524640687b8","source":{"kind":"arxiv","id":"1604.02815","version":1},"attestation_state":"computed","paper":{"title":"Beyond Brightness Constancy: Learning Noise Models for Optical Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Rosenbaum, Yair Weiss","submitted_at":"2016-04-11T07:23:44Z","abstract_excerpt":"Optical flow is typically estimated by minimizing a \"data cost\" and an optional regularizer. While there has been much work on different regularizers many modern algorithms still use a data cost that is not very different from the ones used over 30 years ago: a robust version of brightness constancy or gradient constancy. In this paper we leverage the recent availability of ground-truth optical flow databases in order to learn a data cost. Specifically we take a generative approach in which the data cost models the distribution of noise after warping an image according to the flow and we measu"},"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":"1604.02815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-11T07:23:44Z","cross_cats_sorted":[],"title_canon_sha256":"196de78bd38a5458152e664c5319333da59a463c5e9574bbd9d3a5dd411c1888","abstract_canon_sha256":"95e0becbd115587e2ccffc48559c1dfd91bed3adf81e5f4420f5545d03707911"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:22.086717Z","signature_b64":"mkXkKEUcO4tRrP9T9mByTStNbvLAO8g5cGIwjovwBV3Qn1oFoRfPVHsechJtLWzGC+6RbKGw5A6a0+0xnBA0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28c89daf917c78e9026e0e808a09b12d7074a66e401b49934b4e3524640687b8","last_reissued_at":"2026-05-18T01:17:22.086185Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:22.086185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Brightness Constancy: Learning Noise Models for Optical Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Rosenbaum, Yair Weiss","submitted_at":"2016-04-11T07:23:44Z","abstract_excerpt":"Optical flow is typically estimated by minimizing a \"data cost\" and an optional regularizer. While there has been much work on different regularizers many modern algorithms still use a data cost that is not very different from the ones used over 30 years ago: a robust version of brightness constancy or gradient constancy. In this paper we leverage the recent availability of ground-truth optical flow databases in order to learn a data cost. Specifically we take a generative approach in which the data cost models the distribution of noise after warping an image according to the flow and we measu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.02815","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":""},"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":"1604.02815","created_at":"2026-05-18T01:17:22.086260+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.02815v1","created_at":"2026-05-18T01:17:22.086260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.02815","created_at":"2026-05-18T01:17:22.086260+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDEJ3L4RPR4O","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDEJ3L4RPR4OSATO","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDEJ3L4R","created_at":"2026-05-18T12:30:15.759754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDEJ3L4RPR4OSATOB2AIUCNRFV","json":"https://pith.science/pith/FDEJ3L4RPR4OSATOB2AIUCNRFV.json","graph_json":"https://pith.science/api/pith-number/FDEJ3L4RPR4OSATOB2AIUCNRFV/graph.json","events_json":"https://pith.science/api/pith-number/FDEJ3L4RPR4OSATOB2AIUCNRFV/events.json","paper":"https://pith.science/paper/FDEJ3L4R"},"agent_actions":{"view_html":"https://pith.science/pith/FDEJ3L4RPR4OSATOB2AIUCNRFV","download_json":"https://pith.science/pith/FDEJ3L4RPR4OSATOB2AIUCNRFV.json","view_paper":"https://pith.science/paper/FDEJ3L4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.02815&json=true","fetch_graph":"https://pith.science/api/pith-number/FDEJ3L4RPR4OSATOB2AIUCNRFV/graph.json","fetch_events":"https://pith.science/api/pith-number/FDEJ3L4RPR4OSATOB2AIUCNRFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDEJ3L4RPR4OSATOB2AIUCNRFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDEJ3L4RPR4OSATOB2AIUCNRFV/action/storage_attestation","attest_author":"https://pith.science/pith/FDEJ3L4RPR4OSATOB2AIUCNRFV/action/author_attestation","sign_citation":"https://pith.science/pith/FDEJ3L4RPR4OSATOB2AIUCNRFV/action/citation_signature","submit_replication":"https://pith.science/pith/FDEJ3L4RPR4OSATOB2AIUCNRFV/action/replication_record"}},"created_at":"2026-05-18T01:17:22.086260+00:00","updated_at":"2026-05-18T01:17:22.086260+00:00"}