{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PQQOSC3KBO5QW6EWZAS5VAIG4J","short_pith_number":"pith:PQQOSC3K","schema_version":"1.0","canonical_sha256":"7c20e90b6a0bbb0b7896c825da8106e27639f69f209ef17817d4f39f92f2ed40","source":{"kind":"arxiv","id":"2407.15642","version":2},"attestation_state":"computed","paper":{"title":"Cinemo: Consistent and Controllable Image Animation with Motion Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cunjian Chen, Gengyun Jia, Xin Ma, Xinyuan Chen, Yaohui Wang, Yuan-Fang Li, Yu Qiao","submitted_at":"2024-07-22T14:00:03Z","abstract_excerpt":"Diffusion models have achieved great progress in image animation due to powerful generative capabilities. However, maintaining spatio-temporal consistency with detailed information from the input static image over time (e.g., style, background, and object of the input static image) and ensuring smoothness in animated video narratives guided by textual prompts still remains challenging. In this paper, we introduce Cinemo, a novel image animation approach towards achieving better motion controllability, as well as stronger temporal consistency and smoothness. In general, we propose three effecti"},"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":"2407.15642","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T14:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"319f19f6e877879f550538a0264e2e0cfa4a07dd1dc708467e2a5e755fe4efa5","abstract_canon_sha256":"83d733b426c5b82448539711b93757f3ba944c39b4ba43d4888edb1c85c2ecc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:23.185931Z","signature_b64":"Q58CY0bons5B3AGEMtzsx6aFS0dvd1NFGzSSVnrbQ6m4UTozCs2gygKwQxfxuFA0wSy/lJacGZc/kXmsW3VuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c20e90b6a0bbb0b7896c825da8106e27639f69f209ef17817d4f39f92f2ed40","last_reissued_at":"2026-07-05T08:47:23.185394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:23.185394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cinemo: Consistent and Controllable Image Animation with Motion Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cunjian Chen, Gengyun Jia, Xin Ma, Xinyuan Chen, Yaohui Wang, Yuan-Fang Li, Yu Qiao","submitted_at":"2024-07-22T14:00:03Z","abstract_excerpt":"Diffusion models have achieved great progress in image animation due to powerful generative capabilities. However, maintaining spatio-temporal consistency with detailed information from the input static image over time (e.g., style, background, and object of the input static image) and ensuring smoothness in animated video narratives guided by textual prompts still remains challenging. In this paper, we introduce Cinemo, a novel image animation approach towards achieving better motion controllability, as well as stronger temporal consistency and smoothness. In general, we propose three effecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15642","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/2407.15642/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":"2407.15642","created_at":"2026-07-05T08:47:23.185463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15642v2","created_at":"2026-07-05T08:47:23.185463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15642","created_at":"2026-07-05T08:47:23.185463+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQQOSC3KBO5Q","created_at":"2026-07-05T08:47:23.185463+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQQOSC3KBO5QW6EW","created_at":"2026-07-05T08:47:23.185463+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQQOSC3K","created_at":"2026-07-05T08:47:23.185463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06280","citing_title":"Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03048","citing_title":"Latte: Latent Diffusion Transformer for Video Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06280","citing_title":"Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06280","citing_title":"Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06280","citing_title":"Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PQQOSC3KBO5QW6EWZAS5VAIG4J","json":"https://pith.science/pith/PQQOSC3KBO5QW6EWZAS5VAIG4J.json","graph_json":"https://pith.science/api/pith-number/PQQOSC3KBO5QW6EWZAS5VAIG4J/graph.json","events_json":"https://pith.science/api/pith-number/PQQOSC3KBO5QW6EWZAS5VAIG4J/events.json","paper":"https://pith.science/paper/PQQOSC3K"},"agent_actions":{"view_html":"https://pith.science/pith/PQQOSC3KBO5QW6EWZAS5VAIG4J","download_json":"https://pith.science/pith/PQQOSC3KBO5QW6EWZAS5VAIG4J.json","view_paper":"https://pith.science/paper/PQQOSC3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15642&json=true","fetch_graph":"https://pith.science/api/pith-number/PQQOSC3KBO5QW6EWZAS5VAIG4J/graph.json","fetch_events":"https://pith.science/api/pith-number/PQQOSC3KBO5QW6EWZAS5VAIG4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQQOSC3KBO5QW6EWZAS5VAIG4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQQOSC3KBO5QW6EWZAS5VAIG4J/action/storage_attestation","attest_author":"https://pith.science/pith/PQQOSC3KBO5QW6EWZAS5VAIG4J/action/author_attestation","sign_citation":"https://pith.science/pith/PQQOSC3KBO5QW6EWZAS5VAIG4J/action/citation_signature","submit_replication":"https://pith.science/pith/PQQOSC3KBO5QW6EWZAS5VAIG4J/action/replication_record"}},"created_at":"2026-07-05T08:47:23.185463+00:00","updated_at":"2026-07-05T08:47:23.185463+00:00"}