{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VD53JGADXUED3KDC26NMXS5HIH","short_pith_number":"pith:VD53JGAD","schema_version":"1.0","canonical_sha256":"a8fbb49803bd083da862d79acbcba741f1e18f5d3dd7dc9fddfde03b413ff163","source":{"kind":"arxiv","id":"2308.10079","version":3},"attestation_state":"computed","paper":{"title":"MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ernie Chu, Jun-Cheng Chen, Shuo-Yen Lin, Tzuhsuan Huang","submitted_at":"2023-08-19T17:59:12Z","abstract_excerpt":"This study introduces an efficient and effective method, MeDM, that utilizes pre-trained image Diffusion Models for video-to-video translation with consistent temporal flow. The proposed framework can render videos from scene position information, such as a normal G-buffer, or perform text-guided editing on videos captured in real-world scenarios. We employ explicit optical flows to construct a practical coding that enforces physical constraints on generated frames and mediates independent frame-wise scores. By leveraging this coding, maintaining temporal consistency in the generated videos ca"},"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":"2308.10079","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-19T17:59:12Z","cross_cats_sorted":[],"title_canon_sha256":"6f4c151e7359541d0a0defb7f38d4609278ab2a6c2311c4878e33b7ae4b64680","abstract_canon_sha256":"d6412f17309807ffb57cb07af45ed89954fe7aa19530b42fc20eb5eeb9c0a15e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:16.448564Z","signature_b64":"HEseQCwQkNYDPOAva48GVLz5O3LMfnbzmCGFOA4cjUzaBXq30h6+uvqgUt794bX6MQHPdRnmWmNW0dANdjiTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8fbb49803bd083da862d79acbcba741f1e18f5d3dd7dc9fddfde03b413ff163","last_reissued_at":"2026-07-05T07:26:16.448094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:16.448094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ernie Chu, Jun-Cheng Chen, Shuo-Yen Lin, Tzuhsuan Huang","submitted_at":"2023-08-19T17:59:12Z","abstract_excerpt":"This study introduces an efficient and effective method, MeDM, that utilizes pre-trained image Diffusion Models for video-to-video translation with consistent temporal flow. The proposed framework can render videos from scene position information, such as a normal G-buffer, or perform text-guided editing on videos captured in real-world scenarios. We employ explicit optical flows to construct a practical coding that enforces physical constraints on generated frames and mediates independent frame-wise scores. By leveraging this coding, maintaining temporal consistency in the generated videos ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10079","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/2308.10079/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":"2308.10079","created_at":"2026-07-05T07:26:16.448146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10079v3","created_at":"2026-07-05T07:26:16.448146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10079","created_at":"2026-07-05T07:26:16.448146+00:00"},{"alias_kind":"pith_short_12","alias_value":"VD53JGADXUED","created_at":"2026-07-05T07:26:16.448146+00:00"},{"alias_kind":"pith_short_16","alias_value":"VD53JGADXUED3KDC","created_at":"2026-07-05T07:26:16.448146+00:00"},{"alias_kind":"pith_short_8","alias_value":"VD53JGAD","created_at":"2026-07-05T07:26:16.448146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.18717","citing_title":"Low-Latency Video Anonymization for Crowd Anomaly Detection: Privacy Versus Performance","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VD53JGADXUED3KDC26NMXS5HIH","json":"https://pith.science/pith/VD53JGADXUED3KDC26NMXS5HIH.json","graph_json":"https://pith.science/api/pith-number/VD53JGADXUED3KDC26NMXS5HIH/graph.json","events_json":"https://pith.science/api/pith-number/VD53JGADXUED3KDC26NMXS5HIH/events.json","paper":"https://pith.science/paper/VD53JGAD"},"agent_actions":{"view_html":"https://pith.science/pith/VD53JGADXUED3KDC26NMXS5HIH","download_json":"https://pith.science/pith/VD53JGADXUED3KDC26NMXS5HIH.json","view_paper":"https://pith.science/paper/VD53JGAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10079&json=true","fetch_graph":"https://pith.science/api/pith-number/VD53JGADXUED3KDC26NMXS5HIH/graph.json","fetch_events":"https://pith.science/api/pith-number/VD53JGADXUED3KDC26NMXS5HIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VD53JGADXUED3KDC26NMXS5HIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VD53JGADXUED3KDC26NMXS5HIH/action/storage_attestation","attest_author":"https://pith.science/pith/VD53JGADXUED3KDC26NMXS5HIH/action/author_attestation","sign_citation":"https://pith.science/pith/VD53JGADXUED3KDC26NMXS5HIH/action/citation_signature","submit_replication":"https://pith.science/pith/VD53JGADXUED3KDC26NMXS5HIH/action/replication_record"}},"created_at":"2026-07-05T07:26:16.448146+00:00","updated_at":"2026-07-05T07:26:16.448146+00:00"}