{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WBQ2B3MUDZ6PZGZRYAILXOZOER","short_pith_number":"pith:WBQ2B3MU","schema_version":"1.0","canonical_sha256":"b061a0ed941e7cfc9b31c010bbbb2e24402ff2dc927541deb1dc00e26091994f","source":{"kind":"arxiv","id":"2409.16160","version":2},"attestation_state":"computed","paper":{"title":"MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liefeng Bo, Miaomiao Cui, Yifang Men, Yuan Yao","submitted_at":"2024-09-24T15:00:07Z","abstract_excerpt":"Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community, 3D works typically require multi-view captures for per-case training, which severely limits their applicability of modeling arbitrary characters in a short time. Recent 2D methods break this limitation via pre-trained diffusion models, but they struggle for pose generality and scene interaction. To this end, we propose MIMO, a novel framework which can not only synthesize character videos with controllable attributes"},"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":"2409.16160","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-24T15:00:07Z","cross_cats_sorted":[],"title_canon_sha256":"f72e0319135031f9e865e187c73076558c61fbc3b8aaec445bcc9a2ca73c0a37","abstract_canon_sha256":"84b82ab1e72995d85377b05eb65551e3b4f007c3f3ee1079bf8b2dd395ef1afc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:21.230925Z","signature_b64":"1Y/IwkEi3HREoRyuDY89ELZpxfhhHcvvt/2yQMkPSh+5VV2FphtgKvwJK/OInBtdmPTBD+MNXuPLyvuCDXmwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b061a0ed941e7cfc9b31c010bbbb2e24402ff2dc927541deb1dc00e26091994f","last_reissued_at":"2026-07-05T11:19:21.230106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:21.230106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liefeng Bo, Miaomiao Cui, Yifang Men, Yuan Yao","submitted_at":"2024-09-24T15:00:07Z","abstract_excerpt":"Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community, 3D works typically require multi-view captures for per-case training, which severely limits their applicability of modeling arbitrary characters in a short time. Recent 2D methods break this limitation via pre-trained diffusion models, but they struggle for pose generality and scene interaction. To this end, we propose MIMO, a novel framework which can not only synthesize character videos with controllable attributes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16160","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/2409.16160/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":"2409.16160","created_at":"2026-07-05T11:19:21.230229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.16160v2","created_at":"2026-07-05T11:19:21.230229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16160","created_at":"2026-07-05T11:19:21.230229+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBQ2B3MUDZ6P","created_at":"2026-07-05T11:19:21.230229+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBQ2B3MUDZ6PZGZR","created_at":"2026-07-05T11:19:21.230229+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBQ2B3MU","created_at":"2026-07-05T11:19:21.230229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02000","citing_title":"Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09646","citing_title":"VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":274,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WBQ2B3MUDZ6PZGZRYAILXOZOER","json":"https://pith.science/pith/WBQ2B3MUDZ6PZGZRYAILXOZOER.json","graph_json":"https://pith.science/api/pith-number/WBQ2B3MUDZ6PZGZRYAILXOZOER/graph.json","events_json":"https://pith.science/api/pith-number/WBQ2B3MUDZ6PZGZRYAILXOZOER/events.json","paper":"https://pith.science/paper/WBQ2B3MU"},"agent_actions":{"view_html":"https://pith.science/pith/WBQ2B3MUDZ6PZGZRYAILXOZOER","download_json":"https://pith.science/pith/WBQ2B3MUDZ6PZGZRYAILXOZOER.json","view_paper":"https://pith.science/paper/WBQ2B3MU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.16160&json=true","fetch_graph":"https://pith.science/api/pith-number/WBQ2B3MUDZ6PZGZRYAILXOZOER/graph.json","fetch_events":"https://pith.science/api/pith-number/WBQ2B3MUDZ6PZGZRYAILXOZOER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBQ2B3MUDZ6PZGZRYAILXOZOER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBQ2B3MUDZ6PZGZRYAILXOZOER/action/storage_attestation","attest_author":"https://pith.science/pith/WBQ2B3MUDZ6PZGZRYAILXOZOER/action/author_attestation","sign_citation":"https://pith.science/pith/WBQ2B3MUDZ6PZGZRYAILXOZOER/action/citation_signature","submit_replication":"https://pith.science/pith/WBQ2B3MUDZ6PZGZRYAILXOZOER/action/replication_record"}},"created_at":"2026-07-05T11:19:21.230229+00:00","updated_at":"2026-07-05T11:19:21.230229+00:00"}