{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JIZFPYTMCGJQLZS76LWCS4LPYH","short_pith_number":"pith:JIZFPYTM","schema_version":"1.0","canonical_sha256":"4a3257e26c119305e65ff2ec29716fc1c5f041b4e22cbd275e66e303f2723002","source":{"kind":"arxiv","id":"1906.05928","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised Video Interpolation Using Cycle Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Tao, Aysegul Dundar, Bryan Catanzaro, Deqing Sun, Fitsum A. Reda, Guilin Liu, Jan Kautz, Kevin J. Shih, Mohammad Shoeybi","submitted_at":"2019-06-13T21:04:10Z","abstract_excerpt":"Learning to synthesize high frame rate videos via interpolation requires large quantities of high frame rate training videos, which, however, are scarce, especially at high resolutions. Here, we propose unsupervised techniques to synthesize high frame rate videos directly from low frame rate videos using cycle consistency. For a triplet of consecutive frames, we optimize models to minimize the discrepancy between the center frame and its cycle reconstruction, obtained by interpolating back from interpolated intermediate frames. This simple unsupervised constraint alone achieves results compara"},"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":"1906.05928","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-13T21:04:10Z","cross_cats_sorted":[],"title_canon_sha256":"8dbaa9fa5ee3532f806cd83d816f84ec75a999019e105dc9f4042a96ee05edd1","abstract_canon_sha256":"ceb4db713094e39b90c0e3fb5587f21f02724370b5fd2e8c503964908d9d543c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:45.632152Z","signature_b64":"k+y68iuXMg7C7WdYN21PLBuCuWBJYxtYlUfsfVulavfrvMoY+Jnge/rwu2BgOOngZFelxga8HWBEVbu/OVpkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a3257e26c119305e65ff2ec29716fc1c5f041b4e22cbd275e66e303f2723002","last_reissued_at":"2026-07-05T02:26:45.631594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:45.631594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Video Interpolation Using Cycle Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Tao, Aysegul Dundar, Bryan Catanzaro, Deqing Sun, Fitsum A. Reda, Guilin Liu, Jan Kautz, Kevin J. Shih, Mohammad Shoeybi","submitted_at":"2019-06-13T21:04:10Z","abstract_excerpt":"Learning to synthesize high frame rate videos via interpolation requires large quantities of high frame rate training videos, which, however, are scarce, especially at high resolutions. Here, we propose unsupervised techniques to synthesize high frame rate videos directly from low frame rate videos using cycle consistency. For a triplet of consecutive frames, we optimize models to minimize the discrepancy between the center frame and its cycle reconstruction, obtained by interpolating back from interpolated intermediate frames. This simple unsupervised constraint alone achieves results compara"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05928","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/1906.05928/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":"1906.05928","created_at":"2026-07-05T02:26:45.631653+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05928v3","created_at":"2026-07-05T02:26:45.631653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05928","created_at":"2026-07-05T02:26:45.631653+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIZFPYTMCGJQ","created_at":"2026-07-05T02:26:45.631653+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIZFPYTMCGJQLZS7","created_at":"2026-07-05T02:26:45.631653+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIZFPYTM","created_at":"2026-07-05T02:26:45.631653+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.02749","citing_title":"Video Interpolation and Prediction with Unsupervised Landmarks","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JIZFPYTMCGJQLZS76LWCS4LPYH","json":"https://pith.science/pith/JIZFPYTMCGJQLZS76LWCS4LPYH.json","graph_json":"https://pith.science/api/pith-number/JIZFPYTMCGJQLZS76LWCS4LPYH/graph.json","events_json":"https://pith.science/api/pith-number/JIZFPYTMCGJQLZS76LWCS4LPYH/events.json","paper":"https://pith.science/paper/JIZFPYTM"},"agent_actions":{"view_html":"https://pith.science/pith/JIZFPYTMCGJQLZS76LWCS4LPYH","download_json":"https://pith.science/pith/JIZFPYTMCGJQLZS76LWCS4LPYH.json","view_paper":"https://pith.science/paper/JIZFPYTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05928&json=true","fetch_graph":"https://pith.science/api/pith-number/JIZFPYTMCGJQLZS76LWCS4LPYH/graph.json","fetch_events":"https://pith.science/api/pith-number/JIZFPYTMCGJQLZS76LWCS4LPYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIZFPYTMCGJQLZS76LWCS4LPYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIZFPYTMCGJQLZS76LWCS4LPYH/action/storage_attestation","attest_author":"https://pith.science/pith/JIZFPYTMCGJQLZS76LWCS4LPYH/action/author_attestation","sign_citation":"https://pith.science/pith/JIZFPYTMCGJQLZS76LWCS4LPYH/action/citation_signature","submit_replication":"https://pith.science/pith/JIZFPYTMCGJQLZS76LWCS4LPYH/action/replication_record"}},"created_at":"2026-07-05T02:26:45.631653+00:00","updated_at":"2026-07-05T02:26:45.631653+00:00"}