{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LXY7C3CIIPKL3RWQYGSWSEMQRL","short_pith_number":"pith:LXY7C3CI","schema_version":"1.0","canonical_sha256":"5df1f16c4843d4bdc6d0c1a56911908ac3616d38ff77bb2687c4a9169ad10422","source":{"kind":"arxiv","id":"2311.16933","version":1},"attestation_state":"computed","paper":{"title":"SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anyi Rao, Bo Dai, Ceyuan Yang, Dahua Lin, Maneesh Agrawala, Yuwei Guo","submitted_at":"2023-11-28T16:33:08Z","abstract_excerpt":"The development of text-to-video (T2V), i.e., generating videos with a given text prompt, has been significantly advanced in recent years. However, relying solely on text prompts often results in ambiguous frame composition due to spatial uncertainty. The research community thus leverages the dense structure signals, e.g., per-frame depth/edge sequences, to enhance controllability, whose collection accordingly increases the burden of inference. In this work, we present SparseCtrl to enable flexible structure control with temporally sparse signals, requiring only one or a few inputs, as shown i"},"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":"2311.16933","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T16:33:08Z","cross_cats_sorted":[],"title_canon_sha256":"778edd37d3d9d00a292035dbf3e5be2fa9a9c2f9d2912b5d0e6ca5210c96741c","abstract_canon_sha256":"876238ecdb9b03dfdb20a4da65f5e90c8d7d6f94e29ecbfcbc63b9da84f8e0c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:48.550705Z","signature_b64":"6sSV/oHyHAoHf77M053XXwP8xI1X3LnwH/Y1/es8jIpTf5fcKcGdWjRbijHa2vIMg/4JLO3gJbXRAc7V+IKICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5df1f16c4843d4bdc6d0c1a56911908ac3616d38ff77bb2687c4a9169ad10422","last_reissued_at":"2026-07-05T07:17:48.550179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:48.550179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anyi Rao, Bo Dai, Ceyuan Yang, Dahua Lin, Maneesh Agrawala, Yuwei Guo","submitted_at":"2023-11-28T16:33:08Z","abstract_excerpt":"The development of text-to-video (T2V), i.e., generating videos with a given text prompt, has been significantly advanced in recent years. However, relying solely on text prompts often results in ambiguous frame composition due to spatial uncertainty. The research community thus leverages the dense structure signals, e.g., per-frame depth/edge sequences, to enhance controllability, whose collection accordingly increases the burden of inference. In this work, we present SparseCtrl to enable flexible structure control with temporally sparse signals, requiring only one or a few inputs, as shown i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16933","kind":"arxiv","version":1},"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/2311.16933/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":"2311.16933","created_at":"2026-07-05T07:17:48.550237+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.16933v1","created_at":"2026-07-05T07:17:48.550237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16933","created_at":"2026-07-05T07:17:48.550237+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXY7C3CIIPKL","created_at":"2026-07-05T07:17:48.550237+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXY7C3CIIPKL3RWQ","created_at":"2026-07-05T07:17:48.550237+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXY7C3CI","created_at":"2026-07-05T07:17:48.550237+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24107","citing_title":"DramaDirector: Geometry-Guided Short Drama Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18576","citing_title":"DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21431","citing_title":"iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02509","citing_title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2404.02101","citing_title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00658","citing_title":"UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LXY7C3CIIPKL3RWQYGSWSEMQRL","json":"https://pith.science/pith/LXY7C3CIIPKL3RWQYGSWSEMQRL.json","graph_json":"https://pith.science/api/pith-number/LXY7C3CIIPKL3RWQYGSWSEMQRL/graph.json","events_json":"https://pith.science/api/pith-number/LXY7C3CIIPKL3RWQYGSWSEMQRL/events.json","paper":"https://pith.science/paper/LXY7C3CI"},"agent_actions":{"view_html":"https://pith.science/pith/LXY7C3CIIPKL3RWQYGSWSEMQRL","download_json":"https://pith.science/pith/LXY7C3CIIPKL3RWQYGSWSEMQRL.json","view_paper":"https://pith.science/paper/LXY7C3CI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.16933&json=true","fetch_graph":"https://pith.science/api/pith-number/LXY7C3CIIPKL3RWQYGSWSEMQRL/graph.json","fetch_events":"https://pith.science/api/pith-number/LXY7C3CIIPKL3RWQYGSWSEMQRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXY7C3CIIPKL3RWQYGSWSEMQRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXY7C3CIIPKL3RWQYGSWSEMQRL/action/storage_attestation","attest_author":"https://pith.science/pith/LXY7C3CIIPKL3RWQYGSWSEMQRL/action/author_attestation","sign_citation":"https://pith.science/pith/LXY7C3CIIPKL3RWQYGSWSEMQRL/action/citation_signature","submit_replication":"https://pith.science/pith/LXY7C3CIIPKL3RWQYGSWSEMQRL/action/replication_record"}},"created_at":"2026-07-05T07:17:48.550237+00:00","updated_at":"2026-07-05T07:17:48.550237+00:00"}