{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KY4VWYWA62MDLUW652LJXOMMP5","short_pith_number":"pith:KY4VWYWA","schema_version":"1.0","canonical_sha256":"56395b62c0f69835d2deee969bb98c7f4d500b191e63725a9aaca6f718e53615","source":{"kind":"arxiv","id":"2412.11284","version":1},"attestation_state":"computed","paper":{"title":"Learning Normal Flow Directly From Event Neighborhoods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cornelia Ferm\\\"uller, Dehao Yuan, Jiayi Wu, Jingxi Chen, Levi Burner, Minghui Liu, Yiannis Aloimonos","submitted_at":"2024-12-15T19:09:45Z","abstract_excerpt":"Event-based motion field estimation is an important task. However, current optical flow methods face challenges: learning-based approaches, often frame-based and relying on CNNs, lack cross-domain transferability, while model-based methods, though more robust, are less accurate. To address the limitations of optical flow estimation, recent works have focused on normal flow, which can be more reliably measured in regions with limited texture or strong edges. However, existing normal flow estimators are predominantly model-based and suffer from high errors.\n  In this paper, we propose a novel su"},"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":"2412.11284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-15T19:09:45Z","cross_cats_sorted":[],"title_canon_sha256":"a03e943a9e00ba57902bee7333639cd67f36ef11c606252d4180f3e3e24e331a","abstract_canon_sha256":"fa14f0247c31d75180716d71132d7d96594d19b8f4545f6d95bd83c074bdd10b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:30.004093Z","signature_b64":"TI/9LTGjZLGaAR0QFsQmZvX2kwz6V418eWnpM/ILwAiBcccGtdnhglCA6tNcePV3R66i7L8sHVkC1WhIYzuEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56395b62c0f69835d2deee969bb98c7f4d500b191e63725a9aaca6f718e53615","last_reissued_at":"2026-07-05T09:49:30.003576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:30.003576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Normal Flow Directly From Event Neighborhoods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cornelia Ferm\\\"uller, Dehao Yuan, Jiayi Wu, Jingxi Chen, Levi Burner, Minghui Liu, Yiannis Aloimonos","submitted_at":"2024-12-15T19:09:45Z","abstract_excerpt":"Event-based motion field estimation is an important task. However, current optical flow methods face challenges: learning-based approaches, often frame-based and relying on CNNs, lack cross-domain transferability, while model-based methods, though more robust, are less accurate. To address the limitations of optical flow estimation, recent works have focused on normal flow, which can be more reliably measured in regions with limited texture or strong edges. However, existing normal flow estimators are predominantly model-based and suffer from high errors.\n  In this paper, we propose a novel su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11284","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/2412.11284/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":"2412.11284","created_at":"2026-07-05T09:49:30.003645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11284v1","created_at":"2026-07-05T09:49:30.003645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11284","created_at":"2026-07-05T09:49:30.003645+00:00"},{"alias_kind":"pith_short_12","alias_value":"KY4VWYWA62MD","created_at":"2026-07-05T09:49:30.003645+00:00"},{"alias_kind":"pith_short_16","alias_value":"KY4VWYWA62MDLUW6","created_at":"2026-07-05T09:49:30.003645+00:00"},{"alias_kind":"pith_short_8","alias_value":"KY4VWYWA","created_at":"2026-07-05T09:49:30.003645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24604","citing_title":"LC-Flow: Learning Local Continuous Optical Flow and Confidence from events","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KY4VWYWA62MDLUW652LJXOMMP5","json":"https://pith.science/pith/KY4VWYWA62MDLUW652LJXOMMP5.json","graph_json":"https://pith.science/api/pith-number/KY4VWYWA62MDLUW652LJXOMMP5/graph.json","events_json":"https://pith.science/api/pith-number/KY4VWYWA62MDLUW652LJXOMMP5/events.json","paper":"https://pith.science/paper/KY4VWYWA"},"agent_actions":{"view_html":"https://pith.science/pith/KY4VWYWA62MDLUW652LJXOMMP5","download_json":"https://pith.science/pith/KY4VWYWA62MDLUW652LJXOMMP5.json","view_paper":"https://pith.science/paper/KY4VWYWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11284&json=true","fetch_graph":"https://pith.science/api/pith-number/KY4VWYWA62MDLUW652LJXOMMP5/graph.json","fetch_events":"https://pith.science/api/pith-number/KY4VWYWA62MDLUW652LJXOMMP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KY4VWYWA62MDLUW652LJXOMMP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KY4VWYWA62MDLUW652LJXOMMP5/action/storage_attestation","attest_author":"https://pith.science/pith/KY4VWYWA62MDLUW652LJXOMMP5/action/author_attestation","sign_citation":"https://pith.science/pith/KY4VWYWA62MDLUW652LJXOMMP5/action/citation_signature","submit_replication":"https://pith.science/pith/KY4VWYWA62MDLUW652LJXOMMP5/action/replication_record"}},"created_at":"2026-07-05T09:49:30.003645+00:00","updated_at":"2026-07-05T09:49:30.003645+00:00"}