{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FHKII4RKDRZ6QDKVB2XEQFHY25","short_pith_number":"pith:FHKII4RK","schema_version":"1.0","canonical_sha256":"29d484722a1c73e80d550eae4814f8d75ffa6c0578ecdd79dd71bdb9cb972bf8","source":{"kind":"arxiv","id":"2405.20222","version":3},"attestation_state":"computed","paper":{"title":"MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Muyao Niu, Xiaodong Cun, Xintao Wang, Ying Shan, Yinqiang Zheng, Yong Zhang","submitted_at":"2024-05-30T16:22:22Z","abstract_excerpt":"We present MOFA-Video, an advanced controllable image animation method that generates video from the given image using various additional controllable signals (such as human landmarks reference, manual trajectories, and another even provided video) or their combinations. This is different from previous methods which only can work on a specific motion domain or show weak control abilities with diffusion prior. To achieve our goal, we design several domain-aware motion field adapters (\\ie, MOFA-Adapters) to control the generated motions in the video generation pipeline. For MOFA-Adapters, we con"},"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":"2405.20222","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T16:22:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb61d529e5a6d6ea889c8c61b9a46775bb2614aba3f68f2411cfea6fe854755c","abstract_canon_sha256":"4ae55a98cf84c5d6260b70fd11e83f5a2608504d25395463df6ce2eb3fabd857"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:36.567769Z","signature_b64":"pIgj7hj+bw9aylxnzsHv6ZjPFnS0tL1qrYIwFd8G28N5nOzfFwrgXxgoihpCYzfzFMeHf3yXJT2uGZES+Qb+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29d484722a1c73e80d550eae4814f8d75ffa6c0578ecdd79dd71bdb9cb972bf8","last_reissued_at":"2026-07-05T08:42:36.567304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:36.567304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Muyao Niu, Xiaodong Cun, Xintao Wang, Ying Shan, Yinqiang Zheng, Yong Zhang","submitted_at":"2024-05-30T16:22:22Z","abstract_excerpt":"We present MOFA-Video, an advanced controllable image animation method that generates video from the given image using various additional controllable signals (such as human landmarks reference, manual trajectories, and another even provided video) or their combinations. This is different from previous methods which only can work on a specific motion domain or show weak control abilities with diffusion prior. To achieve our goal, we design several domain-aware motion field adapters (\\ie, MOFA-Adapters) to control the generated motions in the video generation pipeline. For MOFA-Adapters, we con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20222","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/2405.20222/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":"2405.20222","created_at":"2026-07-05T08:42:36.567374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20222v3","created_at":"2026-07-05T08:42:36.567374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20222","created_at":"2026-07-05T08:42:36.567374+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHKII4RKDRZ6","created_at":"2026-07-05T08:42:36.567374+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHKII4RKDRZ6QDKV","created_at":"2026-07-05T08:42:36.567374+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHKII4RK","created_at":"2026-07-05T08:42:36.567374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.00503","citing_title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02048","citing_title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FHKII4RKDRZ6QDKVB2XEQFHY25","json":"https://pith.science/pith/FHKII4RKDRZ6QDKVB2XEQFHY25.json","graph_json":"https://pith.science/api/pith-number/FHKII4RKDRZ6QDKVB2XEQFHY25/graph.json","events_json":"https://pith.science/api/pith-number/FHKII4RKDRZ6QDKVB2XEQFHY25/events.json","paper":"https://pith.science/paper/FHKII4RK"},"agent_actions":{"view_html":"https://pith.science/pith/FHKII4RKDRZ6QDKVB2XEQFHY25","download_json":"https://pith.science/pith/FHKII4RKDRZ6QDKVB2XEQFHY25.json","view_paper":"https://pith.science/paper/FHKII4RK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20222&json=true","fetch_graph":"https://pith.science/api/pith-number/FHKII4RKDRZ6QDKVB2XEQFHY25/graph.json","fetch_events":"https://pith.science/api/pith-number/FHKII4RKDRZ6QDKVB2XEQFHY25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHKII4RKDRZ6QDKVB2XEQFHY25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHKII4RKDRZ6QDKVB2XEQFHY25/action/storage_attestation","attest_author":"https://pith.science/pith/FHKII4RKDRZ6QDKVB2XEQFHY25/action/author_attestation","sign_citation":"https://pith.science/pith/FHKII4RKDRZ6QDKVB2XEQFHY25/action/citation_signature","submit_replication":"https://pith.science/pith/FHKII4RKDRZ6QDKVB2XEQFHY25/action/replication_record"}},"created_at":"2026-07-05T08:42:36.567374+00:00","updated_at":"2026-07-05T08:42:36.567374+00:00"}