{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KPFCTL2HBW6YXP6S2TKCHGXBWF","short_pith_number":"pith:KPFCTL2H","schema_version":"1.0","canonical_sha256":"53ca29af470dbd8bbfd2d4d4239ae1b15fb2830929b33147e35c83edd8710dda","source":{"kind":"arxiv","id":"2203.13674","version":2},"attestation_state":"computed","paper":{"title":"Dense Continuous-Time Optical Flow from Events and Frames","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Davide Scaramuzza, Manasi Muglikar, Mathias Gehrig","submitted_at":"2022-03-25T14:29:41Z","abstract_excerpt":"We present a method for estimating dense continuous-time optical flow from event data. Traditional dense optical flow methods compute the pixel displacement between two images. Due to missing information, these approaches cannot recover the pixel trajectories in the blind time between two images. In this work, we show that it is possible to compute per-pixel, continuous-time optical flow using events from an event camera. Events provide temporally fine-grained information about movement in pixel space due to their asynchronous nature and microsecond response time. We leverage these benefits to"},"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":"2203.13674","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-25T14:29:41Z","cross_cats_sorted":[],"title_canon_sha256":"53c90e473478fa13aa0393d7c91708faa9d05cd9834b3e3224d0cbe40fd9ee2d","abstract_canon_sha256":"0d77fc57fb5947f2e09d2396d24394cb10d6ca43a0072ff2d42738363919a6a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:50.056038Z","signature_b64":"utf0EPumArtvQPsnWSKwMjdrRfMzvNgnAlKW4ky67uXQ40nOvBbhpQBocBEN207Lo7CiucUqxxiMYElq0VOWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53ca29af470dbd8bbfd2d4d4239ae1b15fb2830929b33147e35c83edd8710dda","last_reissued_at":"2026-07-05T07:43:50.055627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:50.055627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense Continuous-Time Optical Flow from Events and Frames","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Davide Scaramuzza, Manasi Muglikar, Mathias Gehrig","submitted_at":"2022-03-25T14:29:41Z","abstract_excerpt":"We present a method for estimating dense continuous-time optical flow from event data. Traditional dense optical flow methods compute the pixel displacement between two images. Due to missing information, these approaches cannot recover the pixel trajectories in the blind time between two images. In this work, we show that it is possible to compute per-pixel, continuous-time optical flow using events from an event camera. Events provide temporally fine-grained information about movement in pixel space due to their asynchronous nature and microsecond response time. We leverage these benefits to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13674","kind":"arxiv","version":2},"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/2203.13674/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":"2203.13674","created_at":"2026-07-05T07:43:50.055675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.13674v2","created_at":"2026-07-05T07:43:50.055675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13674","created_at":"2026-07-05T07:43:50.055675+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPFCTL2HBW6Y","created_at":"2026-07-05T07:43:50.055675+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPFCTL2HBW6YXP6S","created_at":"2026-07-05T07:43:50.055675+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPFCTL2H","created_at":"2026-07-05T07:43:50.055675+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21187","citing_title":"Making Every Event Count: Balancing Data Efficiency and Accuracy in Event Camera Subsampling","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPFCTL2HBW6YXP6S2TKCHGXBWF","json":"https://pith.science/pith/KPFCTL2HBW6YXP6S2TKCHGXBWF.json","graph_json":"https://pith.science/api/pith-number/KPFCTL2HBW6YXP6S2TKCHGXBWF/graph.json","events_json":"https://pith.science/api/pith-number/KPFCTL2HBW6YXP6S2TKCHGXBWF/events.json","paper":"https://pith.science/paper/KPFCTL2H"},"agent_actions":{"view_html":"https://pith.science/pith/KPFCTL2HBW6YXP6S2TKCHGXBWF","download_json":"https://pith.science/pith/KPFCTL2HBW6YXP6S2TKCHGXBWF.json","view_paper":"https://pith.science/paper/KPFCTL2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.13674&json=true","fetch_graph":"https://pith.science/api/pith-number/KPFCTL2HBW6YXP6S2TKCHGXBWF/graph.json","fetch_events":"https://pith.science/api/pith-number/KPFCTL2HBW6YXP6S2TKCHGXBWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPFCTL2HBW6YXP6S2TKCHGXBWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPFCTL2HBW6YXP6S2TKCHGXBWF/action/storage_attestation","attest_author":"https://pith.science/pith/KPFCTL2HBW6YXP6S2TKCHGXBWF/action/author_attestation","sign_citation":"https://pith.science/pith/KPFCTL2HBW6YXP6S2TKCHGXBWF/action/citation_signature","submit_replication":"https://pith.science/pith/KPFCTL2HBW6YXP6S2TKCHGXBWF/action/replication_record"}},"created_at":"2026-07-05T07:43:50.055675+00:00","updated_at":"2026-07-05T07:43:50.055675+00:00"}