{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ABABX7L24UJQZNTOBLXRXHMF4F","short_pith_number":"pith:ABABX7L2","schema_version":"1.0","canonical_sha256":"00401bfd7ae5130cb66e0aef1b9d85e16e6c0d3161518579cc2a4942953ce164","source":{"kind":"arxiv","id":"2303.09508","version":3},"attestation_state":"computed","paper":{"title":"LDMVFI: Video Frame Interpolation with Latent Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"David Bull, Duolikun Danier, Fan Zhang","submitted_at":"2023-03-16T17:24:41Z","abstract_excerpt":"Existing works on video frame interpolation (VFI) mostly employ deep neural networks that are trained by minimizing the L1, L2, or deep feature space distance (e.g. VGG loss) between their outputs and ground-truth frames. However, recent works have shown that these metrics are poor indicators of perceptual VFI quality. Towards developing perceptually-oriented VFI methods, in this work we propose latent diffusion model-based VFI, LDMVFI. This approaches the VFI problem from a generative perspective by formulating it as a conditional generation problem. As the first effort to address VFI using l"},"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":"2303.09508","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2023-03-16T17:24:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e64ff8ad893ae8ff2b1b40d2d5f75cac7058fb281c0f35763cf0f6caf17ad9e8","abstract_canon_sha256":"5fe1a6f829abc0e1ef223046fbff20eb8ba65a1ed37766f454fce3711492b817"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:14.427497Z","signature_b64":"bzq3zWtUGkL1EkrShof4blb1iHJQB2C+AR4T4zyPdHSsHhyl4hiv8+2dwgsEwRV79ggjsis3v3Riaw5MWzdACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00401bfd7ae5130cb66e0aef1b9d85e16e6c0d3161518579cc2a4942953ce164","last_reissued_at":"2026-07-05T08:29:14.426989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:14.426989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LDMVFI: Video Frame Interpolation with Latent Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"David Bull, Duolikun Danier, Fan Zhang","submitted_at":"2023-03-16T17:24:41Z","abstract_excerpt":"Existing works on video frame interpolation (VFI) mostly employ deep neural networks that are trained by minimizing the L1, L2, or deep feature space distance (e.g. VGG loss) between their outputs and ground-truth frames. However, recent works have shown that these metrics are poor indicators of perceptual VFI quality. Towards developing perceptually-oriented VFI methods, in this work we propose latent diffusion model-based VFI, LDMVFI. This approaches the VFI problem from a generative perspective by formulating it as a conditional generation problem. As the first effort to address VFI using l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09508","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/2303.09508/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":"2303.09508","created_at":"2026-07-05T08:29:14.427055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09508v3","created_at":"2026-07-05T08:29:14.427055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09508","created_at":"2026-07-05T08:29:14.427055+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABABX7L24UJQ","created_at":"2026-07-05T08:29:14.427055+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABABX7L24UJQZNTO","created_at":"2026-07-05T08:29:14.427055+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABABX7L2","created_at":"2026-07-05T08:29:14.427055+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00843","citing_title":"Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ABABX7L24UJQZNTOBLXRXHMF4F","json":"https://pith.science/pith/ABABX7L24UJQZNTOBLXRXHMF4F.json","graph_json":"https://pith.science/api/pith-number/ABABX7L24UJQZNTOBLXRXHMF4F/graph.json","events_json":"https://pith.science/api/pith-number/ABABX7L24UJQZNTOBLXRXHMF4F/events.json","paper":"https://pith.science/paper/ABABX7L2"},"agent_actions":{"view_html":"https://pith.science/pith/ABABX7L24UJQZNTOBLXRXHMF4F","download_json":"https://pith.science/pith/ABABX7L24UJQZNTOBLXRXHMF4F.json","view_paper":"https://pith.science/paper/ABABX7L2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09508&json=true","fetch_graph":"https://pith.science/api/pith-number/ABABX7L24UJQZNTOBLXRXHMF4F/graph.json","fetch_events":"https://pith.science/api/pith-number/ABABX7L24UJQZNTOBLXRXHMF4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABABX7L24UJQZNTOBLXRXHMF4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABABX7L24UJQZNTOBLXRXHMF4F/action/storage_attestation","attest_author":"https://pith.science/pith/ABABX7L24UJQZNTOBLXRXHMF4F/action/author_attestation","sign_citation":"https://pith.science/pith/ABABX7L24UJQZNTOBLXRXHMF4F/action/citation_signature","submit_replication":"https://pith.science/pith/ABABX7L24UJQZNTOBLXRXHMF4F/action/replication_record"}},"created_at":"2026-07-05T08:29:14.427055+00:00","updated_at":"2026-07-05T08:29:14.427055+00:00"}